An improved wavelet-based dereverberation for robust automatic speech recognition

This paper presents an improved wavelet-based dereverberation method for automatic speech recognition (ASR). Dereverberation is based on filtering reverberant wavelet coefficients with the Wiener gains to suppress the effect of the late reflections. Optimization of the wavelet parameters using acoustic model enables the system to estimate the clean speech and late reflections effectively. This results to a better estimate of the Wiener gains for dereverberation in the ASR application. Additional tuning of the parameters of the Wiener gain in relation with the acoustic model further improves the dereverberation process for ASR. In the experiment with real reverberant data, we have achieved a significant improvement in ASR accuracy. Index Terms: Robustness, Speech recognition, Dereverberation

[1]  Hamid Sheikhzadeh,et al.  An improved wavelet-based speech enhancement system , 2001, INTERSPEECH.

[2]  K. Shikano,et al.  Fast Dereverberation for Hands-Free Speech Recognition , 2008, 2008 Hands-Free Speech Communication and Microphone Arrays.

[3]  Kiyohiro Shikano,et al.  Distant talking robust speech recognition using late reflection components of room impulse response , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  Hans-Günter Hirsch,et al.  A new approach for the adaptation of HMMs to reverberation and background noise , 2008, Speech Commun..

[5]  David L. Donoho,et al.  De-noising by soft-thresholding , 1995, IEEE Trans. Inf. Theory.

[6]  Tatsuya Kawahara,et al.  Optimization of dereverberation parameters based on likelihood of speech recognizer , 2009, INTERSPEECH.

[7]  Eliathamby Ambikairajah,et al.  Wavelet transform-based speech enhancement , 1998, ICSLP.

[8]  Michael S. Brandstein,et al.  WAVELET TRANSFORM EXTREMA CLUSTERING FOR MULTI-CHANNEL SPEECH DEREVERBERATION , 1999 .

[9]  Mohammad T. Manzuri Shalmani,et al.  An improved wavelet-based speech enhancement by using speech signal features , 2006, Comput. Electr. Eng..

[10]  Tomohiro Nakatani,et al.  Spectral Subtraction Steered by Multi-Step Forward Linear Prediction For Single Channel Speech Dereverberation , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[11]  F. Asano,et al.  An optimum computer‐generated pulse signal suitable for the measurement of very long impulse responses , 1995 .

[12]  Tatsuya Kawahara,et al.  Optimizing spectral subtraction and wiener filtering for robust speech recognition in reverberant and noisy conditions , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.