Method and apparatus for providing an improved feature set in sp

Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G10L 1520

Patent

active

060980400

ABSTRACT:
The invention relates to a method and apparatus for generating noise-attenuated feature vectors for use in recognizing speech, more particularly to a system and method providing a feature set for speech recognition that is robust to adverse noise conditions. This is done by receiving, through an input, a set of signal frames, at least some containing speech sounds, and then classifying the frames in the set of signal frames into classification groups on the basis of their energy levels. Each classification group is characterized by a mean energy value. In a specific example of implementation, the invention makes use of channel energy values to condition the frames in the set of signal frames. The frames in the set of signal frames are attenuated or noise reduced by altering the energy of the frames on the basis of the frames containing non-speech sounds. In a specific example of implementation, the invention compresses the energy of the frames in the set of signal frames such that the energy lies within a range. The invention also allows separate energy ranges to be defined for each channel.

REFERENCES:
patent: 4164025 (1979-08-01), Dubnowski et al.
patent: 4630304 (1986-12-01), Borth et al.
patent: 4751737 (1988-06-01), Gerson et al.
patent: 4797910 (1989-01-01), Daudelin
patent: 4897878 (1990-01-01), Boll et al.
patent: 4918732 (1990-04-01), Gerson et al.
patent: 4959855 (1990-09-01), Daudelin
patent: 4979206 (1990-12-01), Padden et al.
patent: 5050215 (1991-09-01), Nishimura
patent: 5052038 (1991-09-01), Shepard
patent: 5086479 (1992-02-01), Takenaga et al.
patent: 5091947 (1992-02-01), Ariyoshi et al.
patent: 5097509 (1992-03-01), Lennig
patent: 5127055 (1992-06-01), Larkey
patent: 5163083 (1992-11-01), Dowden et al.
patent: 5181237 (1993-01-01), Dowden et al.
patent: 5204894 (1993-04-01), Darden
patent: 5212764 (1993-05-01), Ariyoshi
patent: 5274695 (1993-12-01), Green
patent: 5307444 (1994-04-01), Tsuboka
patent: 5488652 (1996-01-01), Bielby et al.
patent: 5515475 (1996-05-01), Gupta et al.
patent: 5732388 (1998-03-01), Hoege et al.
Furui, Digital Speech Processing, Synthesis, and Recognition, Marcel Dekker, Inc., New York, (1989), pp. 55-56, 225-232, 1989.
"Putting Speech Recognition to Work in the Telephone Network," IEEE Computer Society, vol. 23, No. 8, Aug. 1990, pp. 335-341.
Dynamic Adaptation of Hidden Markov Model for Robust Speech Recognition, IEEE International Symposium on Circuits and Systems, vol. 2, May 1989, pp. 1336-1339.
A Fast Search Strategy in a Large Vocabulary Word Recognizer, V.N. Gupta et al., INRS-Telecommunications, J. Acoust. Soc. Am. 84(6), Dec. 1988, pp. 2007-2017.
Unleashing the Potential of Human-to-Machine Communication, Lennig et al., Teleis, Issue 97, 1993, pp. 23-27.
An Introduction to Hidden Markov Models, L.R. Rabiner and B.H. Juang, IEEE ASSP Magazine, Jan. 1986, pp. 4-16.
Putting speech Recognition to Work in the Telephoen Network, Matthew Lenning, Proc. of IEEE, Aug. 1990, pp. 35-40.
Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences, Steven B. Davies and Paul Mermelstein, IEEE Trans. ASSP, ASSP-28, 1980, pp. 357-366.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Method and apparatus for providing an improved feature set in sp does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for providing an improved feature set in sp, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for providing an improved feature set in sp will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-673298

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.