Speaker diarization of meetings based on large TDOA feature vectors

This paper investigates the use of large TDOA feature vectors together with acoustic information in speaker diarization of meetings. TDOAs are obtained by considering all possible microphones pairs and this approach is compared with conventional TDOA features extracted w.r.t. a reference channel. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Vijayasenan, D., Valente, F.
Format: Conference Proceeding
Language:English
Subjects:
Acoustics
Delay
Hidden Markov models
Meetings Recordings
Microphones
Model combination
NIST
Speaker diarization
Speech
Time Delay Of Arrival features
Vectors
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper investigates the use of large TDOA feature vectors together with acoustic information in speaker diarization of meetings. TDOAs are obtained by considering all possible microphones pairs and this approach is compared with conventional TDOA features extracted w.r.t. a reference channel. The study is carried using two systems, the first based on Gaussian Mixture Modeling and the second based on the Information Bottleneck approach. Results on NIST RT06/RT07/RT09 evaluation datasets show a large speaker error reduction of 30% relative going from 14.3% to 10.8% for the first and from 12.3% to 8.2% for the second whenever the feature weighting is properly handled. Furthermore results reveal that the IB system is more robust to different number of microphones even when all pairs large TDOA vectors are used thus outperforming the HMM/GMM by 25% relative (8.2% error compared to 10.8%).
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2012.6288838