The Multimodal Information Group's speech analytics program has a long history of activities supporting the development of technologies that extract content from language-based recordings and of metrology advancements, primarily through systematic and targeted annual evaluations.
Since 1987, the Multimodal Information Group has coordinated several speech transcription technology evaluations that explored several aspects of language production including the domain of discourse, source language, transcription, keyword search, speech/non-speech segmentation (speech activity detection), and disfluency detection, to name a few.
Current speech analytics work:
Past speech analysis work:
Rich Transcription: The Rich Transcription evaluation series promotes and gauges advances in the state-of-the-art in several automatic speech recognition technologies. The goal of the evaluation series is to create recognition technologies that will produce transcriptions which are more readable by humans and more useful for machines.
Lead Organizational Unit:itl