Data processing: speech signal processing – linguistics – language – Speech signal processing – For storage or transmission
Patent
1997-03-18
1999-10-19
Hudspeth, David R.
Data processing: speech signal processing, linguistics, language
Speech signal processing
For storage or transmission
G10L 702
Patent
active
059704454
ABSTRACT:
Hitherto, when speech data is quantized, since a quantum is determined irrespective of a deviation of a distribution of the speech data, an error of an output probability calculation by quantization is large and a recognition rate deteriorates. According to the invention, to solve the subject of the prior art, a quantization range of speech data is obtained, an integral value of an output probability of the quantization range is obtained by using an output probability distribution of statistic models of speech data which has previously been obtained, a quantum is determined so as to equally divide the integral value, and a quantization code book is formed, thereby reducing an error of an output probability due to the quantization and enabling a recognition rate to be improved.
REFERENCES:
patent: 5124701 (1992-06-01), Charbonnier et al.
patent: 5706391 (1998-01-01), Yamada et al.
Wu, Y, et al., A Supervised Learniong Neural Network Coprocessor for Soft-Decision Maximum-Likelihood Decoding, IEEE Transactions on Neural Networks, vol. 6, No. 4, Jul. 1995, pp. 986-992.
Yamaguchi, H., "Optimum Quantization of Laplace Density Signal and Its Characteristics", Electronics and Communications in Japan, May 1984, vol. 67, No. 5, pp. 67-73.
Komori Yasuhiro
Yamamoto Hiroki
Canon Kabushiki Kaisha
Hudspeth David R.
Sofocleous M. David
LandOfFree
Speech recognition using equal division quantization 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 using equal division quantization, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition using equal division quantization will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2069186