Improved speaker diarization system for meetings

Authors:
Elie El-Khoury;Christine Senac;Julien Pinquier
Affiliations:
Toulouse University, IRIT Laboratory, France;Toulouse University, IRIT Laboratory, France;Toulouse University, IRIT Laboratory, France
Venue:
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year:
2009

Citing 0
Cited 5

Face-and-clothing based people clustering in video content

Proceedings of the international conference on Multimedia information retrieval
Speaker role recognition to help spontaneous conversational speech detection

Proceedings of the 2010 international workshop on Searching spontaneous conversational speech
A review on speaker diarization systems and approaches

Speech Communication
Detecting individual role using features extracted from speaker diarization results

Multimedia Tools and Applications
Audiovisual diarization of people in video content

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we investigate new approaches to improve speech activity detection, speaker segmentation and speaker clustering. The main idea behind them is to deal with the problem of speaker diarization for meetings where error rates are relatively high. In opposition to existing methods, a new iterative scheme is proposed considering those three tasks as only one problem. New bidirectional source segmentation is proposed based on the GLR/BIC method. The well-known BIC clustering is also reviewed and a new unsupervised post-processing is added to increase clusters purity. Those new proposals applied on meeting data show a relative improvement of about 40% compared to a standard speaker diarization system.