Speech recognition system accommodating different sources

Details Speech recognition system accommodating different sources Speech recognition system accommodating different sources

1994-01-24

1996-11-05

MacDonald, Allen R.

395 26, G10L 900

Patent

active

055726240

ABSTRACT:
The speech recognition system disclosed herein obtains improved recognition accuracy by employing recognition models which are discriminatively trained from a data base comprising training data from different sources, e.g., both male and female voices. A linear discriminant analysis is performed on the training data using expanded matrices in which sources are identified or labelled. The linear discriminant analysis yields respective transforms for the different sources which however map the different sources onto a common vector space in which the vocabulary models are defined.

REFERENCES:
patent: 4741036 (1988-04-01), Bahl et al.
Haeb-Umbach et al., "Improvements In Connected Digit Recognition Using Linear Discriminant Analysis And Mixture Densities", ICASSP-93, Apr. 27-30, 1993, pp. 239-242.
Wood et al., "Improved Vocabulary Independent Sub-Word HMM Modelling," ICASSP-91, May 14-17, 1991, pp. 181-184.
Aubert et al., "Continuous Mixture Densities And Linear Discriminant Analysis For Improved Context-Dependent Acoustic Models," ICASSP-93, Apr. 27-30, 1993, pp. 648-651.
Ney, "Experiments On Mixture-Density Phoneme-Modelling For The Speaker-Independent 1000-Word Speech Recognition DARPA Task," ICASSP-90, Apr. 3-6, 1990, pp. 713-716.
Hunt et al., "Speaker Dependent And Independent Speech Recognition Experiments With An Auditory Model," ICASSP-88, Apr. 11-14, 1988, pp. 215-218.
Yu et al., "Discriminant Analysis And Supervised Vector Quantization For Continuous Speech Recognition," ICASSP-90, Apr. 3-6, 1990, pp. 685-688.
Ney et al., "Phoneme Modelling Using Continuous Mixture Densities," ICASSP-88, Apr. 11-14, 1988, pp. 437-440.
R. Duda, P. Hart, "Pattern Classification And Scene Analysis" pp. 118-121, Wiley and Sons, 1973.
M. J. Hunt, C. Lefebvre, "A Comparison of Several Acoustic Representations For Speech Recognition With Degraded and Undegraded Speech", Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, Glasgow, Scotland, pp. 262-265, May 1989.
S. A. Zahorian, D. Qian, A. J. Jagharghi, "Acoustic-phonetic Transformations For Improved Speaker-independent Isolated Word Recognition", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, Toronto, Canada, pp. 561-564, May 991.
R. Haeb-Umbach, H. Ney, "Linear Discriminant Analysis For Improved Large Vocabulary Continuous Speech Recognition", Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, San Francisco, CA, pp. 113-116, Mar. 1992.
G. Strang, "Linear Algebra And Its Applications", pp. 343-345, Harcourt Brace Jovanovich, 3rd Ed., 1988.

Affiliated with

Also associated with

Rating

Speech recognition system accommodating different sources does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Speech recognition system accommodating different sources, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition system accommodating different sources will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2021652