Gammatone wavelet Cepstral Coefficients for robust speech recognition

We develop noise robust features using Gammatone wavelets derived from the popular Gammatone functions. These wavelets incorporate the characteristics of human peripheral auditory systems, in particular the spatially-varying frequency response of the basilar membrane. We refer to the new features as Gammatone Wavelet Cepstral Coefficients (GWCC). The procedure involved in extracting GWCC from a speech signal is similar to that of the conventional Mel-Frequency Cepstral Coefficients (MFCC) technique, with the difference being in the type of filterbank used. We replace the conventional mel filterbank in MFCC with a Gammatone wavelet filterbank, which we construct using Gammatone wavelets. We also explore the effect of Gammatone filterbank based features (Gammatone Cepstral Coefficients (GCC)) for robust speech recognition. On AURORA 2 database, a comparison of GWCCs and GCCs with MFCCs shows that Gammatone based features yield a better recognition performance at low SNRs.

[1]  Ralf Schlüter,et al.  Non-stationary feature extraction for automatic speech recognition , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  A. Mertins,et al.  Vocal tract length invariant features for automatic speech recognition , 2005, IEEE Workshop on Automatic Speech Recognition and Understanding, 2005..

[3]  Daniel P. W. Ellis,et al.  Speech and Audio Signal Processing - Processing and Perception of Speech and Music, Second Edition , 1999 .

[4]  Hermann Ney,et al.  Gammatone Features and Feature Combination for Large Vocabulary Speech Recognition , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[5]  Qi Li,et al.  An Auditory-Based Feature Extraction Algorithm for Robust Speaker Identification Under Mismatched Conditions , 2011, IEEE Transactions on Audio, Speech, and Language Processing.

[6]  Chandra Sekhar Seelamantula,et al.  Auditory-motivated Gammatone wavelet transform , 2014, Signal Process..

[7]  Stan Davis,et al.  Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Se , 1980 .

[8]  David Pearce,et al.  The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions , 2000, INTERSPEECH.

[9]  Denis Jouvet,et al.  Evaluation of a noise-robust DSR front-end on Aurora databases , 2002, INTERSPEECH.

[10]  Malcolm Slaney,et al.  An Efficient Implementation of the Patterson-Holdsworth Auditory Filter Bank , 1997 .

[11]  Kuansan Wang,et al.  Auditory representations of acoustic signals , 1992, IEEE Trans. Inf. Theory.

[12]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[13]  J Tchorz,et al.  A model of auditory perception as front end for automatic speech recognition. , 1999, The Journal of the Acoustical Society of America.

[14]  Jorg Kliewer,et al.  The complex-valued continuous wavelet transform as a preprocessor for auditory scene analysis , 1998 .