NOVI, Mich.—Enco Systems will feature its latest advances in five key areas, including captioning, translation, AI production tools, automation and virtual production during IBC2026, set for Sept. 11-14 at the RAI Amsterdam Convention Center.

Several solutions will debut at IBC as Enco demonstrates how broadcasters can apply AI, cloud technologies and intelligent automation across the content life cycle. Highlights include the next generation of Enco’s enCaption technology, the European debut of its enSpeak real-time voice translation solution, new AI tools for television and radio and the IBC debut of the latest Qimera Virtual Production innovations.

IBC highlights will include:

• Captioning: Enco will demonstrate the enCaption suite for automated, highly accurate live captioning. The company will also demo its next-generation enCaption Sierra platform, which offers flexible on-premises and cloud deployment and improvements in language support and accuracy, as well as its Raptor cloud captioning encoder.
• Translation: Enco will show how enTranslate and enSpeak can expand standard captioning capabilities into multilingual text and audio. The enTranslate tool converts live captions into translated text in real time, while enSpeak enables natural-sounding low-latency voice translation.
• Artificial Intelligence: Enco will preview a new AI-powered video solution that automatically identifies and extracts compelling segments from long-form programming for repurposing across social and digital platforms. It will also demonstrate SPOTai, an AI tool that rapidly generates professional video advertisements for television, digital and social media.
• Automation: The company returns to IBC with its VDESK system for visual radio and video production applications and its streamlined A-LIST TV automation system.
• Virtual Production: Enco will showcase Qimera, its Unreal Engine-based real-time 3D compositing platform for immersive virtual environments, augmented reality graphics and dynamic live productions. It will complement Qimera with a whisper-quiet robotic pan/tilt head engineered to position larger camera and lens payloads precisely while supporting VISCA-over-IP control. 

“Broadcasters everywhere are being challenged to do more with less, and Enco offers intelligent, easy-to-use technologies to caption and translate content, create and repurpose programming, automate daily operations and produce compelling live television and radio broadcasts,” Enco President Ken Frommert said.

“European broadcasters operate within very specific staffing and business guidelines, so technology that simplifies workflows and enables smaller teams to accomplish more can have an immediate impact,” he added. “Our IBC showcase demonstrates how Enco is applying AI for audience accessibility and automation/production tools to help broadcasters work more efficiently and increase audience size.”

See Enco at IBC2026 Stand 7.A34. More information is available on the Enco website.

NOVI, Mich.—ENCO has announced a major evolution of its aiTrack dynamic content insertion technology for NAB Show 2026, transforming the original aiTrack workflow into a fully cloud-native, automation-agnostic platform designed for modern broadcast environments.

The company will demo the new features at Booth C2116 in the Central Hall of the LVCC during the show, April 18-22 in Las Vegas.

Built to meet the growing demand for timely, localized and engaging content, aiTrack enables broadcasters to instantly generate, customize and schedule AI-driven audio segments for live and automated programming.

Accessible through any web browser for the first time, aiTrack allows on-air and production teams to create broadcast-ready content in seconds using advanced generative AI models and natural-sounding synthetic voices. From breaking news, entertainment, weather and sports updates to sponsored segments and localized content, the platform delivers seamless insertion into live broadcasts or scheduled playlists across terrestrial and streaming platforms.

“aiTrack represents a fundamental shift in how broadcasters approach content creation and delivery,” said Ken Frommert, President, ENCO. “By removing infrastructure barriers and simplifying AI workflows, we’re giving stations of all sizes the ability to produce high-quality, real-time content that connects with audiences in more meaningful and personalized ways.”

aiTrack's architecture combines large language models, real-time data integration and advanced prompt engineering with high-quality synthetic voice technology. A unique “foundation prompt” framework streamlines complex AI processes into intuitive templates, allowing users to generate consistent, on-brand content simply by entering key variables such as location, format or sponsorship details, according to the company.

The platform’s automation-agnostic design ensures compatibility with any broadcast system, enabling seamless delivery of generated audio files into existing workflows from anywhere in the world. Its role-based interface supports collaboration across teams, while integrated scheduling tools allow users to plan and automate content delivery through a centralized calendar.

aiTrack also introduces significant advancements in audio realism and flexibility, including multi-voice capabilities, language localization and voice cloning technology derived from ENCO’s SPECai platform. These enhancements bring AI-generated audio closer than ever to human performance, enabling broadcasters to maintain a consistent and authentic on-air sound.

As broadcasters navigate staffing challenges and increasing content demands, aiTrack provides a scalable solution that reduces production overhead while expanding creative and revenue opportunities. Stations can deliver more frequent updates, personalize content for local audiences, and incorporate branded or sponsored segments—all while maintaining operational efficiency, according to the company.

“By combining dynamic content generation, flexible scheduling and cloud-based delivery, aiTrack redefines what’s possible in live broadcasting, empowering organizations to do more with less while enhancing audience engagement,” said Frommert.

THUNDER BAY, Ontario—Dougall Media is one of the last privately owned multi-TV, multi-radio, print paper and digital advertising organizations in Canada. We cover all of Northwestern Ontario, a land mass equivalent in size to the Greater Toronto Area but proportionally representng roughly one-tenth of the GTA population.

The Government of Canada’s 2011 DTV transition inspired a complete investment in digital television infrastructure at Dougall Media. We rebuilt the plant to be fully digital from the ground up right from the mandate. As the engineer in charge of technology decisions, I decided to take the extra steps to establish a complete captioning workflow, rather than simply add a digital encoder at the end of the chain.

Accuracy and Automation
We built several different text-to-speech environments, but as time progressed, the expectations for accuracy and deliverability evolved. That inspired a shift to automated captioning solutions that could more easily reach the Canadian Radio-television and Telecommunications Commission (CRTC) minimums for accuracy in captions. We also wanted a system that could address more complex processes, such as speech recognition, without user intervention.

That search led us to ENCO’s enCaption solution for live, automated captioning in 2018. Deployed as a fully on-prem captioning workflow, we have continued to evolve our enCaption solution with nearly every generation, including our most recent update in 2025.

One of the first things we focus on in captioning is accuracy as a measurable outcome; automated captioning must deliver not only strong baseline performance, but consistent results across program types and conditions. As enCaption is designed for real-time broadcast environments, it continues to improve in a way that matters operationally. Our accuracy has continued to improve over time and today hovers near 99%.

This is especially impressive when you consider that the captioning workflow exists within the chaos of many separate audio layers. enCaption’s captioning engine can cleanly differentiate between speech over music, effects-heavy segments, multiple speakers, cross talk and more across our entire 5.1 signal chain.

enCaption has proved it can handle complicated audio streams without creating a constant downstream burden that can cause latency. Accuracy is essential, but if captions arrive too late, viewers lose interest and live programming suffers.

Reliability and consistency are also paramount. Captioning correlates with accessibility, compliance, and viewer experience, and everyone watching (including regulators) notice when it fails. enCaption behaves as part of our core infrastructure, as proven during a primary fiber path outage. Video and audio were restored quickly through a backup satellite feed that didn’t carry usable in-band captions.

We were able to route that baseband backup source through a secondary captioning path and regenerate captions using enCaption. Viewers still received accessible programming, and we remained compliant. That experience reinforced why redundancy and routability were non-negotiable requirements for our automated captioning workflow.

More Than Broadcast
Finally, we’re building systems for a future where linear broadcast is only part of the picture. Connected TV, apps, FAST channels and OTT distribution are rapidly becoming more important. Captioning requirements don’t disappear in that world—they expand, often into translation and multilanguage delivery.

Our continued investment in enCaption allows us to look beyond today’s primary broadcast output across our multiplatform delivery footprint moving forward.

enCaption meets the criteria broadcast engineers value, including accuracy you can measure, exceptional speed with ultra-low latency, performance under challenging audio conditions, flexibility in the signal chain and operational resilience in failures.

ENCO’s customer service has also been exceptional across every phase of our relationship, which is just one more reason we value our decision to standardize on their captioning technology.

More information is available on the ENCO enCaption product page.

NOVI, Mich.—At the 2025 NAB Show, April 6-9 in Las Vegas, ENCO is unveiling a new cloud relay service that establishes a secure connection to on-prem captioning workflows for third-party remote stenographers and captioning services working in live broadcast environments. ENCO’s new CloudCap Delivery Network builds a bridge to ENCO DoCaption closed caption encoders, giving third-party captioners a direct and secure line into the broadcaster’s workflow. CloudCap’s accessibility also provides the broadcaster with the freedom to work with any third-party captioning service operating in the cloud.

CloudCap’s debut coincides with the availability of ENCO’s DoCaption EN848 closed captioning encoder, introduced at NAB New York in October. Now shipping, the DoCaption EN848 provides reliable, automated conversion and delivery of captions and translations produced in-house or via external services. The EN848’s availability provides broadcasters with the opportunity to deploy the system over the IP network, with connectivity to cloud-based captioning services such as those offered by ENCO’s partner Verbit.

The EN848’s core function is to reliably and securely insert closed captions coming from any source in compliance with global captioning standards. Its dual connectivity options also allow broadcasters to deploy redundant captioning workflows with immediate failover from cloud to on-prem automatically-generated captions should connectivity to the cloud service drop. When connected to an EN848, the CloudCap service becomes part of a redundant failsafe solution that ensures broadcasters remain in compliance when faced with technical difficulties. The CloudCap Delivery Network also connects to ENCO DoCaption EN448 encoders for less intensive captioning environments.

Third-party captioners that connect to either encoder via CloudCap have immediate access to the encoder’s user interface to configure the service. CloudCap bypasses traditional configuration of firewall rules and port forwarding to alleviate connectivity challenges. Upon establishing the connection, human captioning services and AI-powered systems can listen to live audio streams coming from the encoder and return a compliant data stream for live broadcast. ENCO DoCaption encoders conform to a broad range of closed captioning specifications, including the encoding and insertion of CEA-608/CEA-708, and Teletext/OP47 ancillary data through standardized and legacy communication protocols.

“Our new EN848 encoder was developed with both CloudCap and our enCaption all-in-one captioning solution in mind to provide our customers with more freedom and choice while ensuring they remain protected through a secure and fully redundant solution,” said Ken Frommert, President, ENCO. “In addition to ensuring 24/7 on-air compliance, we can offer broadcasters a single source of support across their entire closed captioning workflow.”

The EN848 is a 1RU solution featuring a software-defined, FPGA-based ultra-low latency SDI captioning encoder and inserter that can be powered by human or advanced speech recognition (ASR) sources both on-prem and in the cloud. For on-prem workflows, the EN848 offers a specially engineered built-in server to process ASR sources from enCaption systems.

ENCO is exhibiting at W1743 in the West Hall during the show.

It’s become a virtuous circle: Advances in graphics and editing technology lead to higher quality and better-looking content, especially on mobile devices. The audience becomes accustomed to these improvements, which drives the need for further advances in improved quality and content appearance.

Advanced graphics and editing are the unsung heroes of modern video production and the trends and technology that support these heroes will be on full display on the 2025 NAB Show floor in Las Vegas.

As consumers become accustomed to high-quality visual content across all their devices, broadcasters are feeling the pressure to meet these expectations with their own content to stay competitive, according to Sarah Jones, senior technical solutions specialist for Blackmagic Design, Americas.

“This demand means broadcasters are upgrading production equipment and investing in technologies capable of delivering higher resolutions and cinematic images,” Jones says. “While this could impact production budgets, today’s technologies are more accessible than ever before, packing professional features into affordable budgets, so we’re seeing a reduction in the barrier to entry when it comes to the use of cutting-edge technology.”

Standing Out
Uniqueness is also becoming more important in the video graphics and editing sector. With content providers serving out so many channels in an ever more-crowded video universe, being different and eye-catching is vital for building audiences.

As a result, “a significant trend we’re seeing at ENCO Systems is the need for both customizable channel branding and dynamic graphics insertion,” says Bill Bennett, media solutions and
accounts manager for the company.
“Broadcasters and streamers often have the same content feeding several different channels, each requiring its own branding, so they rely on our ClipFire video playout system to separately brand each signal.

“Furthermore, these same folks like to host cost-efficient automated channels with dynamic, compelling graphics which change with real-time data [think weather or sports], so we’ve been able to help them do that, too,” Bennett adds.

Of course, serving out all these extra channels costs money, which is a commodity that content providers cherish. That is why economy is a third trend influencing the graphics and editing sector, with vendors doing their best to devise solutions that deliver advances without emptying the bank.

“​​Whether an individual content creator or a large broadcaster, many are looking to achieve more with less,” Vizrt Chief Marketing Officer Chris Black tells TV Tech. “They’re looking for workflows and technology that can support them creating more content, faster, with multiple aspect ratios for dual outputs, leveraging their current investment without the need to add in new tech, or hire new people. Two big focuses we are seeing are the use of dual-aspect ratios for social media content alongside linear or multiregion
advertising to monetize content across various demographics.”

At the same time, production teams are seeking new ways to scale up their operations that are inherently flexible and efficient. “As a result, we are seeing the further democratization of media technology,” Black says. For instance, “cloud-native and web-based HTML5 graphics platforms with intuitive UI are offering existing graphics templates for individuals to use, increasing efficiency in time to air.”

What They’ll Be Showing
Blackmagic Design will have two booths in South Hall Lower, (SL216 and SL8016), and will showcase cameras, DaVinci Resolve postproduction software and hardware, its wide range of SMPTE-2110 IP video products, the ATEM family of live production switchers, streaming solutions, network storage and more, according to Jones.

“Pairing our URSA Cine Immersive and DaVinci Resolve provides an end-to-end workflow to support these evolving interactive needs, providing the means to capture and edit 8K, 3D video with a 180-degree field of view,” Jones says. “The Blackmagic URSA Cine Immersive is the world’s first commercial camera system designed to capture Apple Immersive Video, and DaVinci Resolve provides the ability to edit Apple Immersive Video for the first time.”

When it comes to automating time-intensive tasks, DaVinci Resolve Studio’s Neural Engine-backed AI tools can significantly speed up workflows. “This comes into play, for example, with our facial recognition technology, which can automatically detect, track and organize footage based on an individual’s face, eliminating the need to search and organize manually,” Jones says. “Similarly, smart reframe tools intelligently resize and reposition footage to fit various aspect ratios, facilitating content repurposing across platforms.

ENCO Systems will showcase its ClipFire flagship multichannel playout and ingest platform which can service a lot of needs (and channels) from a single box, according to Bennett.

“We’ll be showing where we think the future of broadcast graphics are headed, thanks to our Qimera Virtual Production produc,” Bennett says. “Built on the massively popular Unreal Engine, Qimera generates stunning truly three-dimensional graphics which humans can interact with and walk around in 3D space, complete with graphics (and backgrounds) that move as the humans do in-camera, making for some incredibly compelling video. We’ll also be showing the new MOS newsroom automation hooks we’ve built into Qimera recently, to automate the data that’s making those 3D dynamic graphics so compelling.”

Also in the West Hall, Vizrt will demonstrate Viz Connect Audio, “which offers unparalleled connectivity, visibility, and control of audio sources on an NDI network,” Black says. “We are particularly excited about Viz Connect Audio, and how it seamlessly integrates with our flagship TriCaster, the TriCaster Vizion.”

This year’s show will be the first time that the multi-award-winning TriCaster Vizion will be demoed at NAB Show, offering the latest in IP connectivity, configurable SDI I/O, powerful switching, audio mixing and state-of-the-art graphics. “Show attendees can also expect to see advancements in Viz Engine’s seamless integration with Unreal Engine,” Black says. “Building on benchmarks for ease of use and performance, Vizrt will demonstrate—via Viz Arc—enhanced control of the latest versions of Viz Engine 5 and Unreal Engine 5.”

Vizrt also plans to display its latest advances in immersive graphics, cloud, automation, and AI. “We aren’t just showing technology,” Black concludes. “We are showing real-world solutions that solve everyday production challenges across three experience areas and several solution pods.”

NOVI, Mich.—ENCO will debut its first closed-caption encoder during the 2024 NAB Show New York, Oct. 9-10, at the Jacob Javits Center in New York.

The homegrown DoCaption EN848 is now shipping and available separately or as part of ENCO’s enCaption system, giving customers an immediate on-prem or cloud option for fast, automated conversion and delivery of captions and translations, the company said.

The availability of the EN848 allows broadcasters to deploy the system over their IP network, with connectivity to enCaption for cloud-based captioning services such as those offered by ENCO partner VITAC.

The EN848’s dual connectivity options also allow broadcasters to deploy redundant captioning workflows with immediate failover from cloud to on-prem if the network temporarily goes dark.

The solution’s core function is to reliably insert closed captions from any downstream source in compliance with global captioning standards. The EN848 positions ENCO upstream with a truly native solution and pairs the speed and accuracy of enCaption’s automatic conversion with a reliable 1RU solution that maintains broadcasters’ compliance as captions go live to air, it said.

The EN848 conforms to a broad range of closed-captioning specifications, including the encoding and insertion of CEA-608/CEA-708 and Teletext/OP47 ancillary data for standardized and legacy communication protocols, ENCO said.

“While compliance and reliability remain the core function of the closed caption encoder, the EN848 was developed with bigger aspirations in mind,” ENCO President Ken Frommert said.” The EN848 was purpose-built to natively pair with enCaption, removing the need for a third-party device and offer broadcasters a single source of support.”.

See ENCO at 2024 NAB Show New York booth 907

More information is available on the company’s website.

More information on VITAC is available here.

Science fiction books and films have predicted it for years, but now it is actually upon us. Artificial Intelligence is here, and it is being used in the television and film industry.

Like any new tool, the desire is to use AI to improve productivity, while maintaining quality. AI also helps us do tasks that would just be impossible for a single individual to do.

Anyone who has attended a few NAB Shows knows that buzzwords and hot technologies rise and fall, and artificial intelligence is currently the hot technology—expect to find references to AI across the show floor.

“It’s an incredible time to be involved with AI and media right now, and the needs can often be both simple and profound,” said Skip Levens, marketing director for media & entertainment at Quantum. “For example, there are a ton of language models that will transcribe audio and tag it in a video timeline. But what about when you have decades of priceless archival film where multiple people are not just talking over each other, but talking in different languages? That turns out to be great example of where standard tools don’t work well.”

Using AI to recognize what sort of material you want and to understand the languages can streamline an otherwise nearly impossible task.

“We have a customer using Quantum’s ActiveScale Cold Storage solution, offering S3-enabled object storage for hot (active) and cold (inactive) data sets, to support the long-term archiving that reduces cold storage costs by up to 60 percent,” Levens said. “This is especially crucial as companies realize the value that today’s data could hold in the future, whether it be a week or decades from now.”

Next Generation
At the NAB Show, ENCO will unveil enCaption Sierra, the company’s next-generation automated closed-captioning solution. Sierra can pair with ENCO’s enTranslate software to offer live translation to more than 37 languages in real-time.

ENCO will also have some flashy AI possibilities in its NAB Show booth.

“This year, we will highlight how broadcasters can utilize ENCO’s Qimera live virtual production and augmented reality solution,” said Ken Frommert, president of ENCO.  “We will also debut an AI-generated virtual anchor within a 3D space. In our booth, we will use AI and virtual production tools to demonstrate a virtual anchor reporting live news.”

Amazon Web Services (AWS) will be at NAB Show 2024 highlighting each of the company’s six solution areas for media & entertainment operations. Focusing on generative AI, monetization and cloud production, it will use the example of newsroom production as the backdrop of how to apply a number of different solutions.

“Visitors to the AWS booth will also learn how generative AI is being used to enhance viewing experiences for audiences and free up time during production,” said Tracy Geist, global head of media & entertainment for games and sports marketing at AWS. “While AI and machine learning (ML) have already begun to transform broadcast production processes in many ways, our activations at NAB will highlight how the industry is still just scratching the surface of all the day-to-day applications of the technology.”

Geist was eager to give examples of how big customers are using AI to improve both the viewing experience and broadcasters’ production workflows.

“AI is playing a big role in improving the ad-insertion process by making it easier to identify and automate natural ad breaks in content to ensure higher-quality broadcasts,” she said. “Using AI also enables content providers to insert ads that match the context of what’s happening, and more personalized ads based on viewer interests, using tools like Amazon Personalize.”

Geist also said that FOX Sports worked with AWS on its AI-powered Catch Up with Highlights feature, which is powered by Amazon’s open-source Media Replay Engine framework, as well as several AWS services and solutions.

“The engine behind the feature ingests broadcast streams, identifies valuable match moments through AI-trained computer vision, then encodes delivery streams with metadata across user devices,” she said. “By capturing key moments and events as they unfold, Catch Up with Highlights makes it easier for audiences to stay up-to-date with the action, and experience the excitement of the game, regardless of when they start watching.”

Natural Language Companion
At the NAB Show, Nice People At Work (NPAW) will present its newly enhanced version of NaLa, an AI-powered, natural-language companion app that helps video services work with data and the NPAW Suite.

“Our platform provides so much data and so many options for working with it that it can be overwhelming for our smaller and newer customers,” said Till Sudworth, head of the video business unit and member of the management board at NPAW. “At the same time, we wanted to enable even the most seasoned NPAW users to derive faster insights. By streamlining the process of identifying the root causes of errors, we are empowering all our customers with the ability to resolve issues more quickly and cost-effectively.”

Recently updated, NaLa 2.0 is integrated into the NPAW Suite of apps to help streaming operators obtain actionable insights into areas like service performance, viewer-perceived quality, and user behavior. Users can use either voice or text to ask NaLa questions about, for instance, their service’s performance and user engagement, and quickly receive answers in both text and graph formats. NaLa can handle these requests in almost every language in the world.

“Users can also click on a graph to gather in-depth analyses in seconds, revealing hidden trends, anomalies, and key learnings,” Sudworth said. “Additionally, users can request NaLa to create custom dashboards tailored to their specific needs or ask for guidance on how to use the platform.”

AI and its derivatives shows great promise, and the next few years will go a long way in embedding these technologies in our work and private lives. Most of us already have a version of AI in our homes and pockets—think “Alexa” and “Siri”—and AI is already toiling away behind the scene in many industries, including the media & entertainment industry.

The promise is that AI will lead to better, faster and more-targeted information and entertainment. Will the promise live up to the actual implementation?

Ask me in 2030.

Techniques used in newsgathering have changed substantially in the past 20 years, and the same is true for live production. The same mobile technology that shapes what we carry in our pockets has made it faster and easier than ever to cover a breaking news story across town.

News and live-production operations have embraced mobile technology with a vengeance, and it is now widely used across the industry. And every year at the NAB Show, there are sleeker, faster and more capable products.

Staying Connected
Everything hinges on the word “faster,” as we want our news to be right now. The broadcaster who wins the “right now” race is probably the broadcaster that gets the most views.

“With the proliferation of news websites, apps, and social media, audiences expect updates to be shared almost in real-time,” said Matt Scully, director of product management at Dejero. “For film, television and commercial production, teams can leverage a reliable, ultra-fast connection to enable real-time collaboration with dispersed teams and accelerate delivery of content from the set directly to post-production, regardless of location—thus reducing the number of people required on set, and unlocking huge cost-savings.”

Scully pointed out that Dejero’s EnGo 3x with GateWay mode lets news crews broadcast breaking stories, quickly transfer files to prepare and upload packages while in the field, and set up high-bandwidth access points for multiple devices.

With the ability to get signals on the air quickly comes an increasing number of signal sources. Selecting among sources that grow in number can quickly cause a broadcaster to outgrow its source switcher, so TVU Networks will be showing its new solution: TVU MediaHub. MediaHub accepts various input formats ranging from SDI, NDI, SRT and TVU Grid to YouTube and more. It can scale and direct outputs to multiple destinations in formats such as RTMP, HLS, TVU Grid and Facebook. MediaHub can be scaled up or down as needed, and charged by the minute as it is used.

“We’re eager to see how this platform will enable content creators and broadcasters to innovate and engage their audiences in novel, exciting ways,” said Paul Shen, CEO of TVU. “MediaHub is a portal to endless broadcasting possibilities.”

Election Coverage
LiveU will be at the NAB Show demonstrating techniques for election coverage, as well as the company’s latest cloud remote production and sports workflows. The LiveU booth will also host several sessions from leading LiveU EcoSystem partners covering a range of contemporary use cases and workflows, including cloud-remote production, content aggregation and AI-augmented production.

“This will be a record-breaking year for live IP-video, with a very strong roster of global sports events, dozens of elections and other high-profile events all contributing to its growth,” said Steve Wind-Mozley, chief marketing officer at LiveU. “Everything we will showcase at the NAB Show is designed to shorten workflows by reducing complexity and effort, and to add efficiency.”

Virtual studios can make a small space seem much bigger—and the same space can be news one moment, the weather report next and sports after that. Making it all work seamlessly in a live production is the key to virtual production.

ENCO will highlight its Qimera live virtual production and augmented-reality solution for broadcast and production studios. Qimera simplifies the complexities of virtual studio production, enabling broadcasters and content creators to produce immersive content with ease.

“This year, we will highlight how broadcasters can utilize Qimera for augmented reality in addition to virtual production,” said Ken Frommert, president of ENCO. “We will also debut an AI-generated virtual anchor within a 3D space. This is an example of how Qimera blends the physical and digital worlds.”

ENCO will also debut enCaption Sierra, an automated turnkey encoding and captioning system, made possible through ENCO’s recent acquisitions of DoCaption, according to Frommert.

“There will be new features for Sierra that push the boundaries of what has been possible in captioning, and these will be announced closer to NAB. However, we are packing Sierra into an all-in-one system that includes a closed-captioned encoder along with live, automatic captioning software.”

Cloud Environment
EditShare will feature its cloud production and editing service called FLEX, including FLEX Cloud Edit and FLEX Cloud Sync. FLEX Cloud Edit provides media asset management, software-defined storage, and virtual workstations in a cloud environment provided by AWS. FLEX provides a completely open hosting environment, so users are free to use whatever editing software they prefer.

Collecting the news for a local station used to be done entirely in-house, using microwave trucks that beamed a narrow signal back to a dish on a tower at the station. Similarly, live production frequently used satellite uplink trucks to transmit a signal that was received on a big dish at the station—as much as possible, the signal and its processing was kept in-house. That way the engineering department and management could be sure that the station had as much control over the signal path as possible.

In the past 10 to 15 years, that has all changed. Now, news remotes usually use public cellular carriers to send the signals over the internet, often shipping them to cloud facilities for storage and/or processing. Today it is possible to produce a newscast in the cloud with only some anchor feeds coming from the station’s studio.

And don’t be surprised if even that changes in the next couple of years. 

Register for the 2024 NAB Show, April 14-17 in Las Vegas at https://nabshow.com/2024/

LAKE ORION, Mich.—For more than 20 years, Orion Neighborhood Television (ONTV) has been producing three public access channels serving the Lake Orion community, just north of Detroit. These PEG channels include a public access channel, education access channel, and government access channel carried by our local Comcast and AT&T U-verse systems. 

With diverse programming spanning local government meetings, school board meetings, sports, concerts, graduations and our own newscasts and public affairs programs, we produce roughly 800 shows a year. Using Cablecast Community Media software, we make this programming available via broadcast, livestream, and on demand, including our own YouTube channel with thousands of subscribers. Our channels are also accessible using Roku, Fire TV and Apple TV. 

As a 501(c)(3) non-profit entity, we are fortunate to have the generous support of our local government. We have a full HD production facility that we use to produce our shows, and for added revenue, we make it available for commercial use. We also teach production classes, offer internships to college students and co-ops to high school students, and provide grants to our school district’s video program to facilitate technology upgrades. 

 Committed to Captioning
We’re also committed to keeping our media facility up to date. For example, even though ONTV falls below the $3 million annual revenue mark—at which the FCC mandates captioning—we deem it important to make our programming more accessible to the deaf and hard of hearing. After evaluating our options, we chose the ENCO enCaption automated captioning solution. 

We have jumped years ahead in our captioning roadmap since installing enCaption, which we purchased through a county government grant. enCaption automates both live and non-live program captioning in real time with virtually no delay. It’s readily available whenever captions are needed, including for live coverage of government and school board meetings, among other live events. It is also far more affordable than using human captioners.

As meetings are produced and recorded, our Tricaster Mini at the venue feeds an SDI video signal into the Blackmagic 40x40 SDI router in our facility. That signal is then routed through our Cablecast system into enCaption. That program output then flows to our distribution channels, including Comcast, AT&T U-verse, and all our livestreaming platforms. Since our district doesn’t conduct meetings on Friday, we take that time to download our sidecar video files for the week and attach them to our VOD program files.

On-Site Captioning
For in-person attendees who are deaf or hard of hearing, we can also pump captions of the proceedings onto meeting room screens. This involves routing an NDI video signal from enCaption, with the captions over a black screen, back into the Tricaster on site. The auxiliary NDI output of the Tricaster is fed to a meeting control system, which displays it onto video screens next to and above the dais. If multiple people speak over each other, enCaption will zero in on the loudest and screen out others for clarity.

We also use ENCO’s DAD radio automation system to play out audio podcasts we produce, as well as PSAs, music and weather announcements onto our channels and Cablecast message boards. With up to 16 playback modules, DAD supports numerous workflows that include automated ingest, logging, scheduling, playout, programming control and more. 

Between enCaption and DAD, we’re very pleased with the high-quality results we get from these systems. With these reliable, affordable products, ENCO has become critically important to our overall production infrastructure. l

For more information about enCaption and/or DAD, visit www.enco.com.

NOVI, MI.—ENCO has acquired French captioning company DoCaption, a developer and manufacturer of captioning, subtitling, and ancillary data solutions for the broadcast and AV industries. The announcement marks ENCO’s third business acquisition in the past 12 months, following the acquisitions of TranslateTV last July and RUSHWORKS in January. ENCO closed the DoCaption deal on July 1, with ENCO retaining DoCaption’s entire product line, intellectual property, staff, and business operations based in Valence, France.

ENCO says the acquisition will extend its reach into captioning workflows for broadcast and AV applications to offer more complete, integrated and cost-efficient solutions for broadcasters and media companies, such as OTT channels, MVPDs and streaming services. Similarly, ENCO can offer more complete solutions to caption meetings, lectures, and presentations in live AV environments, it said. . ENCO has long worked with DoCaption to deliver live, automated captions  and insert closed captions into live broadcasts. 

ENCO plans to add an entirely new product line with the DoCaption acquisition. DoCaption offers a broad range of broadcast ancillary data solutions that cross the encoding, conversion and transcoding, and monitoring spectrum. DoCaption’s products also include specific solutions for SCTE 104 metadata signaling and insertion for ad markers, SMPTE timecode generation for synchronization, scoreboard data encoding for venue displays and integrated open captions generators and keyers.

DoCaption specializes in developing embedded, integrated hardware and software solutions across its product lines. As DoCaption develops all hardware in-house, ENCO and DoCaption engineers can freely develop more complete solutions with future media workflow opportunities in mind ENCO said.

“DoCaption represents our most strategic acquisition to date as it pertains to future product and business development,” said Ken Frommert, President of ENCO. “Immediately, we can now sell captioning encoders alongside our on-premises and cloud-based enCaption systems to offer more flexible and affordable single-source solutions. Moving forward, our combined team of engineers can work together and leverage DoCaption’s intellectual property to develop new on-board applications that address emerging standards and customer requirements. That includes innovating new solutions that represent a convergence of our strengths to serve future captioning workflows.”

DoCaption products are available globally today and widely used in Europe, Australia and the Americas, according to Co-Founder and Director, Product Management and Worldwide Sales, Renaud Desportes. “We bring strong expertise in broadcast and captioning standards in every part of the world, and understand how to interconnect these different systems,” said Desportes. “Our customers trust us to develop solutions that support various standards, with no frame delay, very fast and smooth response, and very reliable network operation. Working together with ENCO allows us to better serve new customers with continued innovation, global distribution, and advanced support.” 

Launched in 2009 DoCaption provides regular and live captioning solutions for major institutional French TV broadcasters and has also developed fully tailored solutions for Stock Exchange and banks data broadcast, as well as industrial automation systems.

Most broadcasters and content creators got their first taste of the potential of artificial intelligence from closed captioning (aka subtitling). Speech-to-text technology enabled by AI—something many of us already use in our daily lives—has been in use for more than a decade and improvements in its capabilities have become more evident, with far more accuracy in both transcribing as well as translating.

For broadcasters who have to comply with rigid FCC standards, however, the rules are explicit in terms of what type of content is covered as well as its accuracy and even placement on the screen. Vendors have responded to broadcasters’ needs with new tech that make the process more accurate and automated than ever. 

Voice Interaction
Voice Interaction, which began as a live captioning service in 2001 was among the first companies to incorporate AI-based closed captioning when it launched in 2008. Its services and products include automatic live closed captioning, speech transcription, spoken term detection and indexing, spoken language identification and speech analytics for actionable knowledge, compliance logging and broadcast monitoring.

The Portugal-based company has steadily increased its presence in North America, with Scripps and Nexstar among its U.S. customers, and Bell Canada, most of whom use its Audimus.Media platform, a broadcast-grade, AI-driven solution for real-time, automatic closed captioning across multiple platforms, including live TV broadcasting (OTT/OTA), streaming and online meetings. Its speech recognition capabilities extend to 40 languages, with simultaneous translation and speaker differentiation.

Renato Cassaca, chief software development engineer, says the company takes pride in its ability to quickly resolve issues that could result in mispronounced names or inaccurate information on the screen. 

“We have webcrawlers running 24 hours a day that get all the newspapers available online,” he said. “And we also get guest access to the newsroom computer system like AP’s ENPS or Avid iNnews—we have a permanent connection to those systems inside the TV stations and we collect all that data to improve their language models and every day they receive a retrained language model to cope with the changing reality.”

ENCO Systems
ENCO Systems has been a mainstay in the closed-caption market for years with its enCaption automated captioning platform, which it launched in 2010. Since then, AI has advanced far beyond its initial capabilities, and the company has focused on these advances. 

“We’ve been leveraging AI and machine learning for years to get better accuracy and quality out of speech to text,” said Ken Frommert, ENCO CEO for the Detroit-based company. 

“Our ASR [automated speech recognition] engine is actually better in certain situations than a human for live captioning or transcription. As AI has gotten better, it has allowed allowed broadcasters to offer live captioning at significantly less expense, which allows for more programming to be captioned, to not only meet FCC and other regulations  but also being able to leverage captions to search file-based transcriptions.”

(Read more: Captioning for Sports Broadcasting and Venues)

At the NAB Show, ENCO rolled out enCaption5, a cloud-native, microservices-based solution, which adds new features and flexibility such as a caption editor to view and refine the results of offline or previous live transcriptions. enCaption 5 can now add captions to both live and pre-recorded content in 48 languages, combining machine learning with advanced speech-to-text conversion and grammatical structure analysis to deliver exceptional accuracy with extremely low latency. enCaption also now incorporates ENCO’s enTranslate systems as a plug-in.

It also launched AITrack and ENCO-GPT, which leverages the ChatGPT model to generate language responses from text-based queries added to automated TV and radio production workflows. Initially targeting radio, AITrack integrates with ENCO’s DAD radio automation system to generate and insert voice tracks between songs. ENCO-GPT simplifies copy creation within TV and radio broadcasts and program streams and can  automatically create ad copy on behalf of sponsors.

AI-Media
Although the “AI” in Australian based Ai-Media actually stands for “accessibility innovation,” AI/ML is the current driving force behind the 20-year old company’s products and services. 

Much of the company’s first two decades was focused on providing live captioning services but in 2021, the company acquired long-time partner EEG to begin offering EEG’s LEXI automated captioning platform to its customers as well as to help bolster its presence in the North American market.  

It recently launched LEXI 3.0, an improved version of its flagship automatic captioning solution. Independent audits confirm LEXI 3.0 consistently delivers results with 35% fewer recognition, formatting and punctuation errors than the previous version, the company said. The latest version introduces new automated features, including speaker identification and AI-powered caption placement to avoid on-screen interference. The release boosts average quality results from 98.2% to 98.7% Number, Edition Error and Recognition Error (NER).

Combining both an automated AI-based captioning system like Lexi, along with continuing its live captioning service to customers worldwide helps set the company apart, according to John Peck, vice president of international sales.

 “We’re the only captioning supplier where we have all the background of actually producing captioning, whether it be humans and all the different quality levels and the accessibility to make sure that the end user’s needs are met,” he said. “We’re able to be that one vendor that can go from the technology platform all the way through to the service as well.” 

Interra Systems
Interra Systems’ BATON Captions is an automated solution that provides an end-to-end platform from caption generation to QC, auto corrections, review, regeneration and editing. The system is based on machine learning and automatic speech recognition, Natural Language Processing (NLP), which the company says can dramatically expedite the caption creation, QC and verification processes for both live and VOD content, while ensuring a high quality.

Ashish Basu, executive vice president, worldwide sales & business, emphasizes the need for QC in an environment where AI—particularly the buzz around ChatGPT—is hyped as the panacea for captioning accuracy. This attitude can run headlong into regulatory requirements, he added. 

“While AI can generate closed captions with accuracy in the high 90% under ideal circumstances, the reality of television is that circumstances are not always ideal,” Basu recently wrote on tvtechnology.com. “Background noise and heavy accents can quickly degrade the accuracy of AI-generated closed captions. Content owners, however, have no latitude with regulators. They simply cannot blame AI for missing the regulatory mark.

“This is where the hype over ChatGPT and other generative AI solutions runs headlong into the reality of generating closed captions and subtitles,” he cautioned. “If closed captions do not meet regulatory requirements, content owners will be out of compliance and are potentially exposed to devastating business consequences.  

“Not only will the money spent to generate sub-par closed captions have been wasted and more money spent to bring them up to snuff, but also the solid business relationships those content owners are trying to establish with local partners around the world will be threatened,” Basu concluded. 

So while advances in AI are helping make closed captioning more accurate and accessible, we’re still in the early stages. As more broadcasters deploy AI, they will need to balance the need for speed and accuracy with the need to maintain compliance. 

The spoken word in sports is essential to how plays unfold, how athletes observe and interact with one another, and how fans respond to the action. Accessing all this dialog has never been easier nor more entertaining, yet there’s more value to be made.

Technologies are now maturing to inject deeper, live intelligence into these conversations. The allure of having alerts and live searchable access to dramatic vocal interactions at precise moments through instant, automated insights is strong for the sports producer and director. Gaining faster access to game-changing moments on and off the field can only enrich the content available to live production teams and viewers, as well as in post-production. 

Embracing the ‘Third Rail’ of Television
These additional contact points can be enabled by embracing what we call the “’third rail’ of television content. Beyond video and audio, the raw text generated by automatically captioning every microphone feed in a venue can then produce a treasure trove of speech-generated data in real-time. 

That data can then be monitored for any special keywords spoken by people near (or wearing) specific microphones to generate logic metadata flags and alerts and to build a stored dataset of “bread crumbs” that can be hopped through live or at a later time.

Taking the steps to create text transcripts from dozens of microphone feeds requires a philosophical change. Using traditional stenographic methods to generate these captions is simply cost-prohibitive. 

However, thanks to considerable advances in Artificial Intelligence-based Automated Speech Recognition (ASR), it’s now possible to embrace a fast, reliable, and highly accurate technology platform to generate this raw text across many audio channels at the same time. By generating text records of live content, each ASR stream has its own path and can be indexed to its own microphone source (and any associated cameras).

Captioning for Better Live Content
Imagine logging to ASR a specific shotgun microphone or lavalier feed from a specific player known to be particularly chatty at times, and who might state certain words that a producer has determined would be key to that game’s coverage (perhaps related to game-play, other players, weather, or other factors). 

Now imagine you have an ISO camera trained on them, just waiting for a visual moment. Once you start captioning that feed, a back-end automated process can generate an alert telling a producer to look back in the video where keywords were spoken. The result is instant access to that desired live nugget you are seeking. 

Auto racing introduces another interesting use case by leveraging ASR to log and generate transcripts from the race car. Whenever certain drivers mention prescribed keywords, that audio (and video) can be flagged and sent to a producer to consider using for replay in the live broadcast or via social media.

In-Game Replay Applications
In-game replay applications offer another compelling approach. Imagine focusing the microphone and camera on a referee to capture key moments when they mention certain words of importance that the user pre-saved before the show. While you can have an operator log their dialog, not everything can be logged accurately. 

If you have a live ASR running on that referee’s audio feed, with the right software you can perform a text word search on their replay video to navigate to the moments where they stated those words you wanted, enabling faster access during the production. Keyword searches can be done in post-production too, as long as the user saves ASR text transcripts for each microphone feed (which would ideally also has a camera view of the subject to help pinpoint and visualize something of interest).

This treasure trove of speech data can open a whole new world of creative possibilities. No more is a production team limited to what their crew can hear or see and manually decide upon or annotate. With ASR it’s possible to have automated processes that help the user keep an “eye” out for those special moments when certain players or others say the magic words. 

ASR effectively alerts the user to that instant via logic flags, metadata, or other notifications. From there, simply conduct a search backward to the time point indicated by the transcripts to access the audio.

Broadcasters can apply this same technology to tag whenever a play-by-play or PA announcer mentions specific words or names. Did a specific player just do (or say) something interesting? When did the announcer mention that player’s name last? Now the user can search to that point and determine if there’s compelling footage.

While crucial to helping the deaf and hard-of-hearing communities, captions aren’t just about FCC-mandated accessibility anymore. AI-based speech-to-text technology has evolved dramatically over the last few years. Harnessing these improvements in the world of sports opens up endless possibilities to enrich your content and ignite the fan experience to keep them coming back for more. 

Novi, MI—ENCO says it has acquired RUSHWORKS, a supplier of professional production, playback, streaming and robotics for the broadcast and professional AV markets. ENCO will retain the entire RUSHWORKS staff and has opened a new office in a brand-new facility in Highland Village, Texas. RUSHWORKS founder Rush Beesley will continue to lead sales and marketing for the RUSHWORKS product line and ENCO’s automated captioning and translation services into existing RUSHWORKS products.

"ENCO is the global leader in real-time captioning with its patented enCaption technology,” said Beesley. “The integration of its powerful, highly accurate captioning engine with our broadcast automation, integrated PTZ production, and courtroom production and streaming systems will ensure our mutual customers can comply with government regulations and provide critical captioning, transcription and translation services to audiences worldwide.”

Beesley says the merger of ENCO and RUSHWORKS will help the combined company respond to broadcasters’ needs for new production and delivery models, while adding that AV integrators and tech managers are seeking more “powerfully simple” integrated hardware and software solutions that simplify operations inside schools, courtrooms, municipalities and other AV environments.

"In broadcast, over-the-air and cable access TV systems are rapidly converging with OTT models, while radio stations are adding local production tools to support video podcasting and visual radio content,” said Beesley. “On the AV side, our customers now place greater emphasis on building complementary technologies into their workflows that edge closer to complete systems. Our integrated video production systems, specialty robotic production products, and streaming solutions perfectly complement ENCO’s proven live and automated captioning and production systems for these markets worldwide.”

Ken Frommert, President of ENCO, said that RUSHWORKS’s innovations bring a new capacity to ENCO’s product line that further distinguishes the company from competitors. Customers will also benefit from having a single source for technical support across all products and integrated ENCO and RUSHWORKS solutions moving forward.

“The acquisition of RUSHWORKS adds proven technology and talent that opens the door for us to innovate and develop cohesive, integrated broadcast and AV solutions for years to come,” said Frommert. “They also bring strong expertise in video applications, which diversifies our software portfolio to serve a much broader array of business verticals and applications.”

ENCO will formally introduce the RUSHWORKS product line as an ENCO brand at the upcoming ISE 2023 show (Jan. 31-Feb. 3, Fira Barcelona Gran Via, Stand CS544) and the 2023 NAB Show (April 16-19, Booth N5625). 

NOVI, Mich.—ENCO‘s demonstrations at the upcoming IBC2022 exhibition will be highlighted by the European trade show debut of enCaption5, the fifth generation of its AI-enhanced enCaption automated captioning and transcription solution. Exhibiting in stand 8.C75, the company will showcase powerful enhancements including a new, cloud-native architecture; a redesigned user interface; integrated caption editing; expanded multi-language translation capabilities; and a new open API for seamless integration. IBC Show takes place at the RAI Amsterdam, Sept. 9-13.

The award-winning enCaption platform makes it fast, easy, and cost-effective for broadcasters, content producers, and AV professionals to create transcripts and add closed or open captions to both live and pre-recorded content. enCaption combines machine learning with advanced speech-to-text conversion and grammatical structure analysis to deliver exceptional accuracy with extremely low latency.

enCaption5 has been redeveloped from the ground up as a cloud-native solution to take full advantage of public cloud infrastructure, enabling exceptional scalability and flexibility while eliminating the need for on-premises capital equipment when captioning or transcribing file-based content. enCaption5 can also be deployed on-premises or in hybrid on-prem/cloud workflows for customers who need SDI signal connectivity for live captioning or who prefer an on-premises solution.

“Captioning, subtitling, and transcription are increasingly important for broadcasters even beyond regulatory requirements,” said Ken Frommert, President of ENCO. “In addition to making content more inclusively accessible for hard-of-hearing audiences, these functions also make it accessible to non-native-language speakers and the significant percentage of viewers who watch video on their mobile devices with the sound muted. enCaption5 makes deploying and using automated captioning easier and more cost-effective than ever before, and we’re looking forward to showcasing it to IBC attendees.”

KANSAS CITY, MO.—KCCG-TV2 is the government access channel for Kansas City, Mo., airing council meetings, special events and original programming designed to keep residents connected and informed. The 24/7 TV channel is a function of the City Communications Office and on Spectrum, Google Fiber and AT&T U-Verse, and online through Granicus and our YouTube channel.

We have closed captioned our programming for more than 15 years, for regulatory requirements and as a best practice. Until recently, we had been using closed captioners in real time. For government meetings, the captioners would call in via phone line or connect over IP to our Link Electronics 3000 closed caption encoders. They would do the captioning live, and we would record the video with its encoded captions.

We scheduled weekly captioning sessions for our short-form programming, but if we received a new program request from a department or elected official that needed to go on-air more immediately, we had to coordinate with a captioner at the last minute. We also needed to take the time to play back the new show in real time for the captioning to be performed, and if there were any issues along the way, we had to start over—sometimes doing two or three passes.

In all of these cases, we also needed to trim the beginning and end of the captioned recordings, as they were not precisely timed. These were extra steps we wanted to eliminate.

IN-HOUSE DEMO

With so many consumer devices offering various forms of natural voice transcription, I started researching professional solutions for automated closed captioning. Some vendors allowed us to send short video samples for them to run through their system as a test, but the results were usually not very good, and a 20-second video clip wasn’t sufficient to convince us whether or not the systems would meet our needs. In contrast, ENCO allowed us to demo enCaption in-house, which gave us the confidence it would work the way we hoped and eliminate unnecessary steps.

I’m also an engineer, not an accountant, but I know we’re saving a pretty significant amount of money.

Installation of the enCaption system was straightforward—SDI in, SDI out, a network cable, monitor, keyboard and mouse, and we were up and running. The enCaption system takes our master output right before it hits our transmission gear, creating the captions and passing them over IP to our Link 3000 encoder, which then connects to our transmission chain. Our complete live channel is thus captioned 24/7, which we couldn’t afford to do with live stenographers.

The enCaption system has taken many steps out of our day-to-day operations, particularly when putting new programming into rotation. I no longer need to worry about issues like trimming; once our editors have finished a show, I can drop it into our playback system, and call it a day. The enCaption system handles the captioning on the way out.

Ultimately, that efficiency translates into financial savings. We try to use our citizens’ money responsibly, and by saving us time, manpower and operational costs, enCaption allows us to be more productive on a smaller budget.

Joel Cogan is the engineer for KCCGTV2 and has worked at the station for over 18 years. He can be reached atJoel.Cogan@kcmo.org.

For more information, visitenco.comor call 248-827-4440.

WATERTOWN, MASS.—NESN (New England Sports Network) is the broadcast home for the world-champion Boston Red Sox and Boston Bruins. The network is delivered to homes throughout the six-state New England region and nationally as NESN National. Automation and digital content management has almost always been an important part of our broadcast workflow, and the presence of both has only continued to increase since NESN first transitioned to HD.

While discussion around these topics tend to be video-focused, the automation of broadcast audio is a significant component. Audio requires flexibility to move between live and automated playout—especially when it comes to sports programming. Additionally, support for both file-based ingest and surround sound is a must; and on the back-end, business toolsets for monitoring, logging and legal reporting are needed to meet performance requirements and remain in compliance.

CUSTOMIZATION

Our requirements, responsibilities, and goals for audio playout have continued to evolve across our productions. Our evaluations soon led us to ENCO’s DADtv solution.

DADtv is used in our two main studios, with six regular users. There is an immediate benefit to multi-user communities, as all operators can establish their own user profiles. This provides immediate access to each user’s window layout, audio cuts and more, without having to save each session. The system immediately picks up where that user left off, regardless of who else has used the system in between.

User flexibility has naturally been improved. DADtv offers touchscreen and hardware control options; we opted for the latter, as we prefer physical button arrays. The hardware controller (DADpad) provides 10 banks of 40 buttons, providing us with immediate access to 400 audio cuts, more than enough to support our most complex production requirements.

The migration to ENCO allows simplified macro programming of automation. We can now build a small macro set in our Ross Overdrive system that can easily recall a variety of rotating playlists. This allows us to be stylistically discreet about which cuts are used for what broadcast—and overall more fluid in how we manage broadcast audio.

DADtv makes moving between live and automated workflows simple. Maintaining both local and remote control of each server can be a challenge across mixed productions. DADtv’s Universal Translator feature simplifies distinction of manned and unmanned operations by instructing the system to listen for automation commands. In the end, it’s one double-click motion to toggle between the two environments. Once in manual mode, audio engineers have limitless flexibility in how they stack a specific show, choosing from our library of categorized music cuts to match the mood of the event.

DADtv also improves the way we manage content, and comply with various regulations. DADtv’s Dropbox utility automatically ingests audio cuts across a wide network of PCs and workstations and pulls in all associated metadata, creating a far more efficient process than real-time loading. We can now add hundreds of cuts with a single drag-and-drop function.

FLEXIBLE SEARCH

For the first time, we have true search-ability of our audio assets by track title or metadata. If we don’t know the exact cut ID number, we have a variety of efficient search methods available to find the right cut. Real-time ingest also simplifies content management through drag-and-drop functionality that even allows us to pull new cuts into a live broadcast on the fly. This was not an option before.

DADtv provides us with software-defined toolsets to log information around each audio cut, from start time and duration to playout confirmation. This offers an ideal reference point to reconcile that content was broadcast as expected. Queries regarding specific cuts and standard commercial music reporting are easily accommodated with DADtv. The AsPlay log function of the system has been exceedingly valuable in this regard.

DADtv is highly interoperable across multiple platforms, working reliably with our Overdrive system as well SSL C100 audio consoles, GPIO triggers, networked storage servers and digital audio workstations. Overall, moving to DADtv has streamlined our audio production workflow and strengthened how we automate and manage content.

George Morgan is the lead audio engineer for NESN. He can be reached atgmorgan@nesn.com.

For more information on ENCO, visitwww.enco.comor call 248-827-4440.

NEW YORK—Compliance monitoring has evolved over the past decade from simple broadcast logging to what is now a much broader range of applications that encompass monitoring, analysis and even revenue-generating functions for broadcasters, OTT providers and MVPD operators. Today’s digital tools have largely replaced the VHS long-play tape recorders to log transmissions, and other new technologies promise to only increase how broadcasters and others can utilize and even monetize what was once just compliance monitoring.

“The need for compliance loggers comes from the legal requirement to log all broadcasted content,” said Ken Frommert, president of ENCO, a Southfield, Mich.-based provider of broadcast technology systems. “This need, arising from the national telecom regulators, such as the FCC, did not change. However, the ever-increasing economic pressure on the same broadcasters, coupled with the fact the compliance loggers are an economic liability with no real business benefit, will necessarily force a technological evolution that will change the loggers into becoming economically beneficial.”

FROM BROADCAST TO OTT

Compliance monitoring is now at a massive transformational stage.

“To start, while compliance services have their roots in traditional broadcasting, we’re seeing the need for compliance services to not only cover broadcast, but also OTT content,” said Ariff Sidi, chief product officer for content delivery network provider Verizon Digital Media Services. “An increasing number of services now offer the ability to monitor OTT streams, and that trend will continue this year and beyond. We’ll see monitoring capabilities enhanced to cover the full path—from ingestion to delivery and through to the end user experience as well. Second, there will continue to be a major shift from compliance monitoring services being hardware-based to cloud-based.”

Even traditional compliance monitoring is now changing in terms of the content being monitored, the level of detail and even how long to store the results. Much of this wouldn’t have been possible just a few years ago.

“A simple studio-based ‘Air Recorder’ at the output of master control, keeping recordings for 30-90 days is insufficient,” said Ted Korte, COO of Qligent, a Melbourne, Fla.-based developer of broadcast monitoring and QoE technology. “More and more functions are either being outsourced or moved closer to the end user, and so should compliance monitoring. Having a number of monitoring points covering each of the delivery platforms, is a much more accurate representation of an audience and thus creates a more comprehensive compliance verification. Since new regulations are likely to evolve it is also a good practice to record all the associated metadata with the media and to record everything for extended periods of time to allow post verification analysis and audits.”

ORIGINS IN CALM

One of the key components of compliance monitoring is that audio levels are consistent as required by the Commercial Advertisement Loudness Mitigation (CALM) Act, which barred TV commercials—as well as other content—from increasing in volume at commercial breaks. Since the introduction of CALM it has been mostly “all quiet” on the audio front as broadcasters have mostly complied, but new technologies would bring up similar issues.

“Commercial loudness has been an issue since the 1980s, but finally modern audio systems really made it noticeable,” said William T. Hayes, director of engineering for Iowa Public Television and president of the IEEE Broadcast Technology Society. “Today the issue is how people consume content in other ways, and these services don’t follow the rules set in place by CALM. The major streaming services such as Netflix and Amazon Video are pretty good, but then you can instantly tell that YouTube videos and others aren’t CALM-compliant.”

For audio compliance, self-regulation could be one solution, but new technology at the consumer level might also solve the issue.

“The reality is that everyone who has a service that provides video and audio knows they need to do something,” Hayes added. “But self-regulating may not solve all the issues. However, smart TVs could be made to automatically adjust volume to a consistent level.”

FULL STREAM AHEAD

In a recently released white paper, Mediaproxy, a provider of compliance, monitoring and analysis technology noted that as the industry has to deal with an increasing number of transmission platforms that span from traditional broadcasts to OTT logging and monitoring paradigms have also shifted.

“It’s become apparent that with an increase in scale, the tools have to extend in versatility. Making sure that the right content is transmitted at the right place and time across the different outputs is paramount. Loggers are hence expected to have advanced video analysis features like content and source matching” said Erik Otto, Mediaproxy president. "However, this also means that OTT providers will have to address challenges, as streaming doesn’t fit in very well with traditional compliance monitoring."

“Linear and nonlinear streaming is very different as to how it is delivered and consumed, making end-to-end visibility and control much more complex,” said Korte at Qligent. “Streaming is changing all the usual points of reference such as primetime, demographics, DMAs, and even the definition of ‘live’.’’ All this new technology and opportunity will also invite new regulations regarding privacy and data protection [end users], fraud [i.e. advertising], piracy [i.e. rights], ratings [social media], etc. from multiple government agencies as well as vendor/service provider SLAs.”

Yet, unlike in a traditional broadcast, which typically has one version of content delivered to all viewers and with differences often the result of local market requirements, OTT could enable content providers to deliver innumerable discrete streams delivered to users—differentiated by region, device, preference or other factors.

“This same ‘one-to-one’ approach can be applied to compliance monitoring systems, too,” added Sidi. “In addition to monitoring the entire cloud workflow, it can check streams by region or other critical factors.”

The downside for content providers is that these opportunities could require more work.

“Budgets haven’t gone up,” and companies are not hiring replacements when employees leave, according to Hiren Hindocha, CEO of Digital Nirvana. “However today’s new compliance monitoring tools can address those requirements.”

AI AND MACHINE LEARNING

Technology could certainly play a major role in this evolution of monitoring and logging, and could take advantage of artificial intelligence or machine learning, which could more easily manage the influx of “Big Data” that is created at a near constant rate.

“The big trend is mixing technical compliance with content compliance,” said ENCO’s Frommert. “The way we see things, the loggers are producing enormous amounts of video data. This ‘Big Data’ is just sitting there for months until it is deleted and replaced by newer data, with no effective use. The use of Big Data technologies is gradually enriching the value of these video records and adding a number of useful functions.”

This, in turn could change compliance monitoring from something required and which can be costly, into a potential revenue stream instead.

Compliance tools are required by law, and thus become an expense for broadcasters, Hayes said, who added that today, AI can turn compliance into a value add instead.

“AI can analyze your audio for CALM compliance, but could also make it easier to ensure that closed captioning makes sense, including that the right version of a word is used. But it can also turn it into a profit center as it becomes a service, whether that is a tool for viewers to find content, or for those in commercial broadcasting so that advertisers and vendors can track their results.”

This could include automated detection of commercial ad spots, which could replace what has been a manually intensive work.

“This technology [AI] can scan many channels and provide very accurate affidavit reports on the number of ad spots,” added Frommert. “Similarly, the ads watching technology can also analyze competing channels and provide comparisons channel to channel on the number of ads sold and aired.”

AI could further automatically create captions and subtitles via speech recognition technology, while also utilizing rich metadata for searching and organizing the vast archives of video, which are stored on-premise or in the cloud.

“This can make it easier for people to find the content they want, as it is needs to be available to whomsoever, whenever they want it,” said Hindocha. “Metadata is really ripe for AI and machine learning, as it can help the viewer decide whether they want to consume that content. Metadata, as a side of the logging, helps you slice and dice the variety of content that is out there.”

Automation has been infused into innumerable elements of our daily lives. From production and assembly lines to broadcast facilities around the world, the transition to automated processes and workflows now have deep roots, and have forever changed the way we work, shop and entertain.

A common concern across all appliances of automation is the reduction, or outright elimination, of the human element. While the transition from manual to automated operations will undoubtedly remove human error in many cases, there are certainly more sensitive tasks where the argument for maintaining a manual workflow remains strong.

In the broadcast space, the transition to automated closed-captioning workflows is one topic that breeds intense discussion both for and against. However, the technology has advanced enough to instill confidence with broadcasters in many of today’s top DMAs, clearly representing the future of this important application.

EVOLUTION OF SPEECH-TO-TEXT

Speech recognition dates back to the 1950s, with modest first steps focused on digits and the most basic English words. With consumer services such as Siri and Alexa continuing to improve with each product generation, it’s clear that speed and accuracy in speech-to-text recognition has come a long way. So goes the same with automated captioning technology, which benefits today from the strengths of modern artificial intelligence.

[For an opposing view, read: Is It Live, Or Is It Automated Speech Recognition?]

While different mandates on closed-captioning in broadcast television exist around the world, the unifying purpose ensures that deaf and hearing-impaired viewers can fully understand and enjoy the shows they watch. Beyond the hearing impaired, statistics show that one in six viewers worldwide prefer to receive closed captions with their content.

Production and transmission of live, manual closed captioning has long been challenged by high costs, availability, varied latency, and inconsistent accuracy rates. And it’s true that the transition to more automated, software-defined captioning workflows introduced a new series of challenges.

For example, while automatic speech recognition removes the cost and staffing concerns of manual captioning, the performance of early-generation servers and processors demonstrated accuracy and latency problems. These issues were especially magnified for broadcasters that must now deliver accurate closed captioning across a multichannel, multilingual, multistandard and multiplatform media landscape.

These concerns are rapidly diminishing. The accuracy of speech-to-text conversion across multiple languages continues to improve with the emergence of powerful, deep neural network advances. In fact, accuracy across today’s strongest platforms has been raised to 90 percent or higher. The statistical algorithms associated with these advances, coupled with larger multilingual databases to mine, more effectively interpret—and accurately spell out—the speech coming through the air feed or mix-minus microphone.

Meanwhile, the faster and more powerful processing of computing engines within automated captioning technology has significantly reduced the latency to near real-time. This achievement is particularly impressive given that automated captions took between 30–60 seconds on many systems as recently as one or two generations ago.

Additionally, as closed-captioning software matures, emerging applications to eliminate crosstalk, improve speaker identification and ignore interruptions are improving the overall quality and experience for hearing impaired viewers.

MARCHING FORWARD

Many of the above improvements are related to recent breakthroughs in machine learning technology, which have enabled a deep neural network approach to voice recognition. Machine learning not only strengthens accuracy, it also provides value through detection of different languages and the different ways that people speak.

That intelligence as it relates to different dialects will provide an overall boost to accuracy in closed captioning. Consider a live news operation, where on-premise, automated captioning software now directly integrates with newsroom computer systems without the need for a network connection. This will now help broadcasters strengthen availability—no concerns about a network outage taking the system down—and take advantage of news scripts and rundowns to learn and validate the spelling of local names and terminology. Both of these points were once major and justified arguments against automated captioning.

Automated captioning also enables the applications to be achieved efficiently on a larger scale—costs are lowered due to the transition from human stenographers to computer automation. And as there is a need to caption a growing amount of content, there is an economy of scale that drives the cost down even further as broadcasters automate these processes.

As systems grow more reliable and broadcasters grow more comfortable with the technology, they will also find new efficiencies and opportunities along the way. For one, broadcasters that need to cut into a regularly scheduled program with breaking news or weather alerts will no longer be forced to find qualified (and expensive) live captioners on short notice.

Improvements in captioning technology have also been timely around emerging needs, including networks tasked with captioning large libraries of prerecorded content. As more systems move to software-defined platforms, the captioning workflow for prerecorded and/or long-form content has been greatly simplified. Post-production staff can essentially drag-and-drop video files into a file-based workflow that extracts the audio track for text conversion. These files can then be delivered in various lengths and formats for a TV broadcast, the web, mobile and other platforms.

And with multiplatform reach, broadcasters also have opportunities to caption live and on-demand streams, ensuring that hearing-impaired and multilingual audiences watching online are properly served as well. The future of this technology is very exciting, especially with the knowledge that we’re really just beginning to reap the fruits of this technology.

Ken Frommert is president of ENCO.

SOUTHFIELD, MI–ENCO, a provider of automated workflow and instant playout solutions for radio, television and commercial AV systems, has appointed broadcast industry veteran John Casey as Director of Sales, effective immediately. Reporting to ENCO President Ken Frommert, John will focus specifically on domestic business development across new customers and existing accounts.

John’s broadcast roots run deep, with nearly 30 years of combined experience as a leading broadcast industry publisher and sales and marketing executive. He spent the last 20 years with NewBay Media (recently acquired by Future plc), where he spent the majority of his time leading Radio World Newspaper to record revenues over many consecutive years as Publisher. He was subsequently named Group Publisher of the Media, Entertainment and Technology sector at Future plc immediately following its NewBay Media acquisition.

Prior to his highly successful two-decade run in publishing, John held key sales and marketing roles at Denon Electronics and later Telos Systems, where he served as VP Sales and Marketing. 

"John’s wealth of industry experience and customer-first mentality comes to ENCO at a time of worldwide growth for the company, and having him help to lead the charge in sales across the United States is sure to bring ENCO’s name to many new customers from north to south, east to west,” said Frommert.

SOUTHFIELD, MI—ENCO has announced that its enCaption4 automated captioning solution now supports the NDI protocol for to provide turnkey closed or open captions on live video.

enCaption4 is an on-premise or cloud-based solution featuring a real-time speech to text engine for generating accurate live captioning that live TV and online video require. Now, broadcasters, content producers and commercial AV facilities with an NDI infrastructure can add an automated captioning solution into their workflows. Once connected, enCaption4 can automatically generate captions through its NDI input stream, and output an NDI signal with captions keyed directly on top of the video stream. This capability eliminates the need for specialized encoding hardware.

[Read: Closed-Captioning Technology Evolves]

At the NAB Show, ENCO will demonstrate enCaption4 with this new NDI capability alongside the software-defined solution’s breakthrough accuracy, accelerated speed, extremely low latency, and expanded foreign language support.

“With the growing popularity of NDI, we added NDI support based on customer demand,” said Ken Frommert, President of ENCO. “With NDI support, we’re making it easier for TV networks, local stations and non-traditional broadcasters such as corporations, schools and universities, houses of worship, and webcasters to use our automated captioning solutions within their real-time NDI productions.”