Audio information access from meeting rooms
Steve J. Renals, Daniel P. W. Ellis · 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). · 2004
We investigate approaches to accessing information from the streams of audio data that result from multi-channel recordings of meetings. The methods investigated use word-level transcriptions, and information derived from models of speaker activity and speaker turn patterns. Our experiments include spoken document retrieval for meetings, automatic structuring of meetings based on self-similarity matrices of speaker turn patterns and a simple model of speaker activity. Meeting recordings are rich in both lexical and non-lexical information; our results illustrate some novel kinds of analysis made possible by a transcribed corpus of natural meetings.