A Mathematical Relationship Between Full-Band and

Recently, it has been shown that robustness of au- tomatic speech recognition (ASR) against band-limited additive noises may be improved by multiband ASR (MBASR) approaches. In an -subband MBASR system, the channels in the full-band filterbank are divided into subbands, usually of equal parti- tions, and subband mel-frequency cepstral coefficients (MFCCs) are computed from each filterbank partition using the discrete co- sine transform. However, there is not as yet any analysis on the re- lationship between full-band and multiband MFCCs. In this letter, we show that the th full-band MFCC is the sum of or differ- ence between the th multiband MFCCs multiplied by .

[1]  Hynek Hermansky,et al.  RASTA processing of speech , 1994, IEEE Trans. Speech Audio Process..

[2]  Jean-François Mari,et al.  A recombination model for multi-band speech recognition , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[3]  R. G. Leonard,et al.  A database for speaker-independent digit recognition , 1984, ICASSP.

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

[5]  Hervé Bourlard,et al.  A mew ASR approach based on independent processing and recombination of partial frequency bands , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[6]  S. Boll,et al.  Suppression of acoustic noise in speech using spectral subtraction , 1979 .

[7]  Biing-Hwang Juang,et al.  Signal bias removal by maximum likelihood estimation for robust telephone speech recognition , 1996, IEEE Trans. Speech Audio Process..

[8]  Khalid Daoudi,et al.  A new approach for multi-band speech recognition based on probabilistic graphical models , 2000, INTERSPEECH.

[9]  Yik-Cheung Tam,et al.  Asynchrony with trained transition probabilities improves performance in multi-band speech recognition , 2000, INTERSPEECH.

[10]  Yik-Cheung Tam,et al.  Optimization of sub-band weights using simulated noisy speech in multi-band speech recognition , 2000, INTERSPEECH.

[11]  Alexandros Potamianos,et al.  Multi-band speech recognition in noisy environments , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[12]  Nikki Mirghafori,et al.  Sooner or later: exploring asynchrony in multi-band speech recognition , 1999, EUROSPEECH.

[13]  Roger K. Moore,et al.  Hidden Markov model decomposition of speech and noise , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[14]  Richard M. Stern,et al.  Environment normalization for robust speech recognition using direct cepstral comparison , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.