INTERSPEECH 2004 - ICSLP
8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Speaker-and-Environment Change Detection in Broadcast News using the Common Component GMM-based Divergence Measure

Yih-Ru Wang, Chi-Han Huang

National Chiao Tung University, Taiwan

In this paper, a GMM with common mixture components, referred to as the common component GMM (CCGMM), is proposed to be the signal model for calculating the diversity measure for the speaker-and-environment change detection in broadcast news signal. The use of GMM is to increase the accuracy of audio signal modeling while the use of common mixture components is to solve the complexity problem of parameter estimation and similarity measure evaluation. Experimental results on a TV broadcast news database showed that it outperformed a BIC-based method. A MDR of 21.9% with 16.0% FAR was achieved.

Full Paper

Bibliographic reference.  Wang, Yih-Ru / Huang, Chi-Han (2004): "Speaker-and-environment change detection in broadcast news using the common component GMM-based divergence measure", In INTERSPEECH-2004, 1069-1072.