9th Annual Conference of the International Speech Communication Association

Brisbane, Australia
September 22-26, 2008

A Statistical Model-Based Voice Activity Detection Employing Minimum Classification Error Technique

Sang-Ick Kang, Ji-Hyun Song, Kye-Hwan Lee, Yun-Sik Park, Joon-Hyuk Chang

Inha University, Korea

In this paper, we apply a discriminative weight training to a statistical model-based voice activity detection (VAD). In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratios (LRs) based on a minimum classification error (MCE) method. That approach is different from that of previous works in that different weights are assigned to each frequency bin and is considered to be more realistic. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LR test.

Full Paper

Bibliographic reference.  Kang, Sang-Ick / Song, Ji-Hyun / Lee, Kye-Hwan / Park, Yun-Sik / Chang, Joon-Hyuk (2008): "A statistical model-based voice activity detection employing minimum classification error technique", In INTERSPEECH-2008, 103-106.