ISCA Archive Interspeech 2005
ISCA Archive Interspeech 2005

An improved GMM-based voice quality predictor

Tiago H. Falk, Wai-Yip Chan, Peter Kabal

A voice quality prediction method based on Gaussian mixture models (GMMs) is improved by constructing a feature selection algorithm to provide the best GMM-based prediction quality. The proposed sequential selection algorithm performs N-survivor search, allowing for trading between design complexity and performance. Simulation shows that predictors designed using the proposed algorithm outperform two benchmark selection algorithms. Performance improvements over the ITU-T P.862 PESQ standard are also attained.

doi: 10.21437/Interspeech.2005-814

Cite as: Falk, T.H., Chan, W.-Y., Kabal, P. (2005) An improved GMM-based voice quality predictor. Proc. Interspeech 2005, 2733-2736, doi: 10.21437/Interspeech.2005-814

  author={Tiago H. Falk and Wai-Yip Chan and Peter Kabal},
  title={{An improved GMM-based voice quality predictor}},
  booktitle={Proc. Interspeech 2005},