Title :
Robust speech recognition in additive and channel noise environments using GMM and EM algorithm
Author :
Fujimoto, Masakiyo ; Riki, Y.A.
Author_Institution :
ATR Spoken Language Translation Res. Lab., Kyoto, Japan
Abstract :
In this paper, we evaluated the speech recognition in real driving car environments by using a GMM based speech estimation method and an EM algorithm based channel noise estimation method. The GMM based speech estimation method proposed by Segura et al (2001) was not robust for channel noise such as an acoustic transfer function, a microphone characteristic and so on. To cope with this problem, we propose a channel noise estimation method based on the EM algorithm. Furthermore, we estimate the speech signal more accurately by using a speech GMM and a silence GMM instead of the GMM trained without speech/silence discrimination. Our proposed method has been evaluated on the AURORA3 tasks. In the evaluation results, the proposed method showed the significant improvement in the high-mismatched condition test of AURORA3 tasks.
Keywords :
Gaussian distribution; channel estimation; parameter estimation; speech recognition; AURORA3 tasks; EM algorithm; GMM; Gaussian mixture models; additive noise; car environments; channel noise estimation; robust speech recognition; speech estimation; Acoustic noise; Additive noise; Microphones; Noise robustness; Speech analysis; Speech enhancement; Speech recognition; Testing; Transfer functions; Working environment noise;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on
Print_ISBN :
0-7803-8484-9
DOI :
10.1109/ICASSP.2004.1326142