SpringerOpen Newsletter

Receive periodic news and updates relating to SpringerOpen.

This article is part of the series Multisensor Processing for Signal Extraction and Applications.

Open Access Research Article

Robust Distant Speech Recognition by Combining Multiple Microphone-Array Processing with Position-Dependent CMN

Longbiao Wang*, Norihide Kitaoka and Seiichi Nakagawa

Author Affiliations

Department of Information and Computer Sciences, Toyohashi University of Technology, Toyahashi-shi 441-8580, Japan

For all author emails, please log on.

EURASIP Journal on Advances in Signal Processing 2006, 2006:095491  doi:10.1155/ASP/2006/95491

The electronic version of this article is the complete one and can be found online at: http://asp.eurasipjournals.com/content/2006/1/095491


Received:29 December 2005
Revisions received:20 May 2006
Accepted:11 June 2006
Published:13 August 2006

© 2006 Wang et al.

This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

We propose robust distant speech recognition by combining multiple microphone-array processing with position-dependent cepstral mean normalization (CMN). In the recognition stage, the system estimates the speaker position and adopts compensation parameters estimated a priori corresponding to the estimated position. Then the system applies CMN to the speech (i.e., position-dependent CMN) and performs speech recognition for each channel. The features obtained from the multiple channels are integrated with the following two types of processings. The first method is to use the maximum vote or the maximum summation likelihood of recognition results from multiple channels to obtain the final result, which is called multiple-decoder processing. The second method is to calculate the output probability of each input at frame level, and a single decoder using these output probabilities is used to perform speech recognition. This is called single-decoder processing, resulting in lower computational cost. We combine the delay-and-sum beamforming with multiple-decoder processing or single-decoder processing, which is termed multiple microphone-array processing. We conducted the experiments of our proposed method using a limited vocabulary (100 words) distant isolated word recognition in a real environment. The proposed multiple microphone-array processing using multiple decoders with position-dependent CMN achieved a 3.2% improvement (50% relative error reduction rate) over the delay-and-sum beamforming with conventional CMN (i.e., the conventional method). The multiple microphone-array processing using a single decoder needs about one-third the computational time of that using multiple decoders without degrading speech recognition performance.

References

  1. BH Juang, FK Soong, Hands-free telecommunications. Proceedings of the International Workshop on Hands-Free Speech Communication (HSC '01), April 2001, Kyoto, Japan, 5–10

  2. M Omologo, M Matassoni, P Svaizer, D Giuliani, Experiments of hands-free connected digit recognition using a microphone array. Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, December 1997, Santa Barbara, Calif, USA, 490–497

  3. TB Hughes, H-S Kim, JH DiBiase, HF Silverman, Performance of an HMM speech recognizer using a real-time tracking microphone array as input. IEEE Transactions on Speech and Audio Processing 7(3), 346–349 (1999). Publisher Full Text OpenURL

  4. T Takiguchi, S Nakamura, K Shikano, HMM-separation-based speech recognition for a distant moving speaker. IEEE Transactions on Speech and Audio Processing 9(2), 127–140 (2001). Publisher Full Text OpenURL

  5. ML Seltzer, B Raj, RM Stern, Likelihood-maximizing beamforming for robust hands-free speech recognition. IEEE Transactions on Speech and Audio Processing 12(5), 489–498 (2004). Publisher Full Text OpenURL

  6. S Furui, Cepstral analysis technique for automatic speaker verification. IEEE Transactions on Acoustics, Speech, and Signal Processing 29(2), 254–272 (1981). Publisher Full Text OpenURL

  7. F Liu, RM Stern, X Huang, A Acero, Efficient cepstral normalization for robust speech recognition. Proceedings of the ARPA Speech and Natural Language Workshop, March 1993, Princeton, NJ, USA, 69–74

  8. N Kitaoka, I Akahori, S Nakagawa, Speech recognition under noisy environments using spectral subtraction with smoothing of time direction and real-time cepstral mean normalization. Proceedings of the International Workshop on Hands-Free Speech Communication (HSC '01), April 2001, Kyoto, Japan, 159–162

  9. S Doclo, M Moonen, Robust adaptive time delay estimation for speaker localization in noisy and reverberant acoustic environments. EURASIP Journal on Applied Signal Processing 2003(11), 1110–1124 (2003). Publisher Full Text OpenURL

  10. CH Knapp, GC Carter, The generalized correlation method for estimation of time delay. IEEE Transactions on Acoustics, Speech, and Signal Processing 24(4), 320–327 (1976). Publisher Full Text OpenURL

  11. M Omologo, P Svaizer, Acoustic source location in noisy and reverberant environment using CSP analysis. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '96), May 1996, Atlanta, Ga, USA 2, 921–924

  12. L Wang, N Kitaoka, S Nakagawa, Robust distant speech recognition based on position dependent CMN using a novel multiple microphone processing technique. Proceedings of the 9th European Conference on Speech Communication and Technology (EUROSPEECH '05), September 2005, Lisbon, Portugal, 2661–2664

  13. B Van Veen, K Buckley, Beamforming: a versatile approach to spatial filtering. IEEE ASSP Magazine 5(2), 4–24 (1988)

  14. T Yamada, S Nakamura, K Shikano, Distant-talking speech recognition based on a 3-D Viterbi search using a microphone array. IEEE Transactions on Speech and Audio Processing 10(2), 48–56 (2002). Publisher Full Text OpenURL

  15. J Flanagan, J Johnston, R Zahn, GW Elko, Computer-steered microphone arrays for sound transduction in large rooms. The Journal of the Acoustical Society of America 78(5), 1508–1518 (1985). Publisher Full Text OpenURL

  16. Y Huang, J Benesty, GW Elko, RM Mersereau, Real-time passive source localization: a practical linear-correction least-squares approach. IEEE Transactions on Speech and Audio Processing 9(8), 943–956 (2001). Publisher Full Text OpenURL

  17. M Brandstein, in A framework for speech source localization using sensor arrays, M, ed. by . S. thesis (Brown University, Providence, RI, USA, 1995)

  18. J DiBiase, H Silverman, M Brandstein, Robust localization in reverberant rooms. Microphone Arrays: Signal Processing Techniques and Applications (Springer, Berlin, Germany, 2001), pp. 157–180 chapter 8 OpenURL

  19. V Raykar, B Yegnanarayana, S Prasanna, R Duraiswami, Speaker localization using excitation source information in speech. IEEE Transactions on Speech and Audio Processing 13(5), 751–760 (2005)

  20. Y Bard, Nonlinear Parameter Estimation (Academic Press, New York, NY, USA, 1974)

  21. W Foy, Position-location solutions by Taylor-series estimation. IEEE Transactions on Aerospace and Electronic Systems 12(2), 187–194 (1976)

  22. L Wang, N Kitaoka, S Nakagawa, Distant speech recognition based on position dependent cepstral mean normalization. Proceedings of the 6th IASTED International Conference on Signal and Image Processing (SIP '04), August 2004, Honolulu, Hawaii, USA, 249–254

  23. L Wang, N Kitaoka, S Nakagawa, Robust distant speech recognition based on position dependent CMN. Proceedings of the 9th International Conference on Spoken Language Processing (ICSLP '04), October 2004, Jeju Island, Korea, 2409–2052

  24. A Viterbi, Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Transactions on Information Theory 13(2), 260–269 (1967)

  25. M Omologo, P Svaizer, Use of the crosspower-spectrum phase in acoustic event location. IEEE Transactions on Speech and Audio Processing 5(3), 288–292 (1997). Publisher Full Text OpenURL

  26. S Nakagawa, K Hanai, K Yamamoto, N Minematsu, Comparison of syllable-based HMMs and triphone-based HMMs in Japanese speech recognition. Proceedings of the IEEE Workshop on Automatic Speech Recognition and Understanding, December 1999, Keystone, Colo, USA, 393–396