ISCA Archive Interspeech 2008
ISCA Archive Interspeech 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

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.


doi: 10.21437/Interspeech.2008-23

Cite as: Kang, S.-I., Song, J.-H., Lee, K.-H., Park, Y.-S., Chang, J.-H. (2008) A statistical model-based voice activity detection employing minimum classification error technique. Proc. Interspeech 2008, 103-106, doi: 10.21437/Interspeech.2008-23

@inproceedings{kang08_interspeech,
  author={Sang-Ick Kang and Ji-Hyun Song and Kye-Hwan Lee and Yun-Sik Park and Joon-Hyuk Chang},
  title={{A statistical model-based voice activity detection employing minimum classification error technique}},
  year=2008,
  booktitle={Proc. Interspeech 2008},
  pages={103--106},
  doi={10.21437/Interspeech.2008-23}
}