2920229

Particle Filter Based Non-Stationary Noise Tracking for Robust Speech Recognition

Fujimoto, Masakiyo ; Nakamura, Satoshi

ATR Spoken Language Translation Res. Labs., Kyoto, Japan

1

2005

March 18-23, 2005

257

260

Monte Carlo methods; hidden Markov models; importance sampling; least mean squares methods; sequential estimation; speech recognition; HMM; MMSE-based clean speech estimation; Markov chain Monte Carlo sampling; Metropolis-Hastings sampling; noise robustness; noise sequence estimation; nonstationary noise tracking; particle filter based speech recognition; residual resampling; sequential importance sampling; sequential noise estimation; speech recognition accuracy; Acoustic noise; Collision mitigation; Hidden Markov models; Monte Carlo methods; Noise robustness; Particle filters; Particle tracking; Speech enhancement; Speech recognition; Working environment noise;

English

ieee

Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on

1520-6149

0-7803-8874-7

conf

10.1109/ICASSP.2005.1415099

1415099