Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition

Designing good normalisation to counter the effect of environmental distortions is one of the major challenges for automatic speech recognition (ASR). The Vector Taylor series (VTS) method is a powerful and mathematically well principled technique that can be applied to both the feature and model domains to compensate for both additive and convolutional noises. One of the limitations of this approach, however, is that it is tied to MFCC (and log-filterbank) features and does not extend to other representations such as PLP, PNCC and phase-based front-ends that use power transformation rather than log compression. This paper aims at broadening the scope of the VTS method by deriving a new formulation that assumes a power transformation is used as the non-linearity during feature extraction. It is shown that the conventional VTS, in the log domain, is a special case of the new extended framework. In addition, the new formulation introduces one more degree of freedom which makes it possible to tune the algorithm to better fit the data to the statistical requirements of the ASR back-end. Compared with MFCC and conventional VTS, the proposed approach provides upto 12.2% and 2.0% absolute performance improvements on average, in Aurora-4 tasks, respectively

[1]  Yifan Gong,et al.  An Overview of Noise-Robust Automatic Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[2]  Takao Kobayashi,et al.  Spectral analysis using generalized cepstrum , 1984 .

[3]  Yifan Gong,et al.  Robust Automatic Speech Recognition , 2015 .

[4]  Jon Barker,et al.  Compression of Model-based Group Delay Function for Robust Speech Recognition , 2014 .

[5]  Erfan Loweimi,et al.  A new group delay-based feature for robust speech recognition , 2011, 2011 IEEE International Conference on Multimedia and Expo.

[6]  Hema A. Murthy,et al.  The modified group delay function and its application to phoneme recognition , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[7]  Thierry Dutoit,et al.  Chirp group delay analysis of speech signals , 2007, Speech Commun..

[8]  Rajesh M. Hegde,et al.  Significance of the Modified Group Delay Feature in Speech Recognition , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[9]  Mark J. F. Gales,et al.  Extended VTS for Noise-Robust Speech Recognition , 2011, IEEE Trans. Speech Audio Process..

[10]  H Hermansky,et al.  Perceptual linear predictive (PLP) analysis of speech. , 1990, The Journal of the Acoustical Society of America.

[11]  J. Lim.  Spectral root homomorphic deconvolution system , 1979, ICASSP.

[12]  Yifan Gong,et al.  Improvements to VTS feature enhancement , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[13]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[14]  Jon Barker,et al.  Source-filter separation of speech signal in the phase domain , 2015, INTERSPEECH.

[15]  Richard M. Stern,et al.  A vector Taylor series approach for environment-independent speech recognition , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[16]  Sriram Ganapathy.  Robust speech processing using ARMA spectrogram models , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Keiichi Tokuda,et al.  Mel-generalized cepstral analysis - a unified approach to speech spectral estimation , 1994, ICSLP.

[18]  Li Deng,et al.  HMM adaptation using vector taylor series for noisy speech recognition , 2000, INTERSPEECH.

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

[20]  Richard M. Stern,et al.  Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  Thomas Drugman,et al.  A new phase-based feature representation for robust speech recognition , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[22]  Khe Chai Sim,et al.  Second order vector taylor series based robust speech recognition , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).