NEW YORK—VoiceInteraction will be on the NAB Show New York exhibit floor to highlight how its speech processing technology is being deployed in a pair of products: a Media Monitoring System and the Audimus.Media closed captioning platform.

The Media Monitoring System from VoiceInteraction uses the company’s speech processing and machine learning background, allowing for features like permanent availability of a speech recognition system to retrieve language specific data; a natural language processing engine to analyze, classify and cluster the spoken concepts; identification of known speakers; advertisement identification based on the audio track; program segmentation based on automatic content classification; spoken language detection for multilanguage feeds; and a real-time alert system of non-conforming TV broadcast parameters.

Audimus.Media is VoiceInteraction’s flagship automatic closed captioning system that uses signal processing and machine learning for live shows. It covers the accessibility requirements for live TV broadcasting, internet streaming, VOD publishing and video metadata indexing. It’s newest feature enables it to add closed captions into live video streams encoded with the AV1 video codec in addition to previous supported codecs MPEG2, H.264 and H.265.

VoiceInteraction will be located at booth N464 during NAB Show New York, which takes place Oct. 16-17 at the Javits Convention Center.