Robust speaker change detection

Most commonly used criteria for speaker change detection like log likelihood ratio (LLR) and Bayesian information criterion (BIC) have an adjustable threshold/penalty parameter to make speaker change decisions. These parameters are not always robust to different acoustic conditions and have to be tu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE signal processing letters 2004-08, Vol.11 (8), p.649-651
Main Authors: Ajmera, J., McCowan, I., Bourlard, H.
Format: Article
Language:English
Subjects:
Acoustic signal detection
Adjustable
Bayesian methods
Change detection
Criteria
Data mining
Feature extraction
Likelihood ratio
Loudspeakers
Mathematical models
Maximum likelihood detection
Maximum likelihood estimation
Optimization
Robustness
Streaming media
Streams
Testing
Tuning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most commonly used criteria for speaker change detection like log likelihood ratio (LLR) and Bayesian information criterion (BIC) have an adjustable threshold/penalty parameter to make speaker change decisions. These parameters are not always robust to different acoustic conditions and have to be tuned. In this letter, we present a criterion which can be used to identify speaker changes in an audio stream without such tuning. The criterion consists of calculating the LLR of two models with the same number of parameters. Results on the Hub4 1997 evaluation set indicate that we achieve a performance comparable to using BIC with optimal penalty term.
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2004.831666