Speech recognition with speech density estimation by the dirichlet process mixture

Kenko Ota (1) , Emmanuel Duflos (2, 3) , Philippe Vanheeghe (2, 3) , Masuzo Yanagida

1 LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
2 SEQUEL - Sequential Learning
3 LAGIS-SI

This paper shows a method for the modeling of speech signal distributions based on Dirichlet process mixtures (DPM) and the estimation of noise sequences based on particle filtering. In real situations, the speech recognition rate degrades miser ably because of the effect of environmental noises, reflected waves and so on. To improve the speech recognition rate, a technique for the estimation of noise sequences is necessary. In this paper, the distribution of the clean speech is modeled using the DPM instead of the traditional model, which is a Gaussian mixture model (GMM). Speech signal sequences are generated according to the mean and covariance generated from the DPM. Then, noise signal sequences are estimated with a particle filter. The proposed method using extended Kalman filter (EKF) can improve the speech recognition rate significantly in the low SNR region. Applying unscented Kalman filter (UKF), better results can be obtained in also the high SNR.

Mots clés: Kalman filtering; Signal processing; Speech enhancement; Speech recognition; Stochastic processes

Domaines: Automatique

Kenko Ota, Emmanuel Duflos, Philippe Vanheeghe, Masuzo Yanagida. Speech recognition with speech density estimation by the dirichlet process mixture. IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008., Mar 2008, Las Vegas, United States. pp.1553 - 1556, ⟨10.1109/ICASSP.2008.4517919⟩. ⟨hal-00782333⟩