Publication View

IEEE ICASSP–2003 Hong Kong AUDIO INFORMATION ACCESS FROM MEETING ROOMS (2008)

Abstract
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. 1.

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.8727
Source http://homepages.inf.ed.ac.uk/srenals/pubs/2003/icassp03-mtg.pdf
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English