Signal bias removal for robust telephone speech recognition

Details Signal bias removal for robust telephone speech recognition Signal bias removal for robust telephone speech recognition

1994-03-24

1996-12-31

MacDonald, Allen R.

395 231, 395 242, G10L 302, G10L 900, G10L 506

Patent

active

055902421

ABSTRACT:
A signal bias removal (SBR) method based on the maximum likelihood estimation of the bias for minimizing undesirable effects in speech recognition systems is described. The technique is readily applicable in various architectures including discrete (vector-quantization based), semicontinuous and continuous-density Hidden Markov Model (HMM) systems. For example, the SBR method can be integrated into a discrete density HMM and applied to telephone speech recognition where the contamination due to extraneous signal components is unknown. To enable real-time implementation, a sequential method for the estimation of the bias (SSBR) is disclosed.

REFERENCES:
patent: 4918731 (1990-04-01), Muroi
patent: 5459815 (1995-10-01), Aikawa et al.
Lee, C. H., Lin, C. H., and Juong, B. H., A Study on Speaker Adaptation of the Parameters of Continuous Density Hidden Markov Models, Apr. 1991, IEEE Trans. on Signal Processing, pp. 806-814.
Linde, Y., Buzo, A., and Gray, R. M., An Algorithm for Vector Quantizer Design, Jan, 1980, IEEE Trans. on Communications, pp. 84-95.
Acero, A., "Acoustical and Environmental Robustness in Automatic Speech Recognition," Carnegie Mellon Univ., Pittsburgh, Pa, 141 pages, Sep. 13, 1990.
Acero, A., Stern, R. M., "Environmental Robustness in Automatic Speech Recognition," IEEE, pp. 849-852, 1990.
Aikawa, K., et al., "A Dynamic Cepstrum Incorporating Time-Frequency Masking and Its Application to Continuous Speech Recognition," ICASSP-93--1993 IEEE Int'l Conf. on Acoustics, Speech, and Signal Processing, Minneapolis, Minnesota, pp. II-668-II-671, Apr. 27-30, 1993.
Che, C., et al., "Microphone Arrays and Neural Networks for Robust Speech Recognition," pp. 321-326.
Coz, S. J., Bridle, J. S., "Unsupervised Speaker Adaptation by Probabilistic Spectrum Fitting," IEEE, pp. 294-297.
Furui, S., "Toward Robust Speech Recognition Under Adverse Conditions," pp. 31-42.
Furui, S., "Unsupervised Seaker Adaptation Based on Hierarchical Spectral Clustering," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 37, No. 12, pp. 1923-1930, Dec. 1989.
Gales, M. J. F., Young, S. J., "Cepstral Parameter Compensation for HMM Recognition in Noise," 11 pages, Feb. 9, 1993.
Gales, M. J. F., Young, S. J., "HMM Recognition in Noise Using Parallel Model Combination," 4 pages.
Gales, M. J. F., Young, S. J. "Robust Continuous Speech Recognition Using Parallal Model Combination," CUED/F-INFENG/TR 172, 17 pages, Mar. 1994.
Hermansky, H. "An Efficient Speaker-Independent Automatic Speech Recognition by Simulation of Some Properties of Human Auditory Perception," IEEE, pp. 1159-1162, 1987.
Hermansky, H., et al., "RASTA-PLP Speech Analysis Technique," IEEE, pp. I-121-I-124, 1992.
Hermansky, H., et al., "Recognition of Speech in Additive and Convolutional Noise Based on RASTA Spectral Processing," IEEE, pp. II-83-II-86, 1993.
Juang, B. H., "Speech Recognition in Adverse Environment," Computer Speech and Language, 5, pp. 275-294, 1991.
Juang, B. H., Paliwal, K. K., "Vector Equalization in Hidden Markov Models for Noisy Speech Recognition," IEEE, pp. I-301-I-304, 1992.
Lim, J. S., Oppenheim, A. V., "Enhancement and Bandwidth Compression of Noisy Speech," Proceedings of the IEEE, vol. 67, No. 12, pp. 1586-1604, Dec. 1979.
Liu, F.-H., et al., "Environment Normalization for Robust Speech Recognition Using Direct Cepstral Comparison," 4 pages.
Mellor, B. A., Varga, A. P., "Noise Masking in a Transform Domain," BCC, pp. II-87-II-90, 1993.
Mokbel, C., et al., "On Line Adaptation of a Speech Recognizer to Variations in Telephone Line Conditions," pp. 1247-1250.
Moreno, P. J., Stern, R. M., "Sources of Degradation of Speech Recognition in the Telephone Network," IEEE, pp. I-109-I-112, 1994.
Morgan, N., Hermansky, H., "RASTA Estensions: Robustness to Additive and Convolutional Noise," 4 pages, Sep. 10, 1992.
Neumeyer, L., Weintraub, M. "Probabilistic Optimum Filtering for Robust Speech Recognition," ICASSP '94, 4 pages.
Rose, R. C., Hofstetter, E. M., "Techniques for Robert Word Spotting in Continuous Speech Messages," 4 pages.
Stern, R. M., et al., "Multiple Approaches to Robust Speech Recognition," 6 pages.
Varga, A. P., Moore, R. K., "Hidden Markov Model Decomposition of Speech and Noise," IEEE, pp. 845-848, 1990.
Vaseghi, S. V. Milner, B. P., "Noisy Speech Recognition Based on HMMs, Winer Filters, and Re-evaluation of Most Likely Candidates," IEEE , pp. II-103-II-106, 1993.
Weintraub, M., Neumeyer, L., "Constructing Telephone Acoustic Models from a High-Quality Speech Corpus," ICASSP'94, 4 pages.
Young, S. J., "Cepstral Mean Compensation for HMM Recognition in Noise," pp. 123-126.
Zhao, Y. "Self-Learning Speaker Adaption Based on Spectral Variation Source Decomposition," Speech Communication, pp. 359-362, 1993.

Affiliated with

Also associated with

Rating

Signal bias removal for robust telephone speech recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Signal bias removal for robust telephone speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Signal bias removal for robust telephone speech recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1148282