9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

Comparative Evaluation of Different Methods for Voice Activity Detection

Hongfei Ding, Koichi Yamamoto, Masami Akamine

Toshiba Corporate R&D Center, Japan

This paper presents a comparative evaluation of different methods for voice activity detection (VAD). A novel feature set is proposed in order to improve VAD performance in diverse noisy environments. Furthermore, three classifiers for VAD are evaluated. The three classifiers are Gaussian Mixture Model (GMM), Support Vector Machine (SVM) and Decision Tree (DT). Experimental results show that the proposed feature set achieves better performance than spectral entropy. In the comparison of the classifiers, DT shows the best performance in terms of frame-based VAD accuracy as well as computational cost.

Full Paper

Bibliographic reference.  Ding, Hongfei / Yamamoto, Koichi / Akamine, Masami (2008): "Comparative evaluation of different methods for voice activity detection", In INTERSPEECH-2008, 107-110.