Speech representation by feature-based word prototypes comprisin

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 248, 395 249, 395 25, 395 252, G10L 506

Patent

active

056849257

ABSTRACT:
Digitized speech utterances are converted into phoneme similarity data and regions of high similarity are then extracted and used in forming the word prototype. By alignment across speakers unreliable high phoneme similarity regions are eliminated. Word prototype targets are then constructed comprising the following parameters: the phoneme symbol, the average peak height of the phoneme similarity score, the average peak location and the left and right frame locations. For each target a statistical weight is assigned representing the percentage of occurrences the particular high similarity region occurred across all speakers. The word prototype is feature-based allowing a robust speech representation to be constructed without the need for frame-by-frame analysis.

REFERENCES:
patent: 3770892 (1973-11-01), Clapper
patent: 4481593 (1984-11-01), Bahler
patent: 4489434 (1984-12-01), Moshier
patent: 4489435 (1984-12-01), Moshier
patent: 4528688 (1985-07-01), Ichikawa et al.
patent: 4559602 (1985-12-01), Bates, Jr.
patent: 4624011 (1986-11-01), Watanabe et al.
patent: 4718094 (1988-01-01), Bahl et al.
patent: 4723290 (1988-02-01), Watanabe et al.
patent: 4736429 (1988-04-01), Niyada et al.
patent: 4742547 (1988-05-01), Watanabe
patent: 4748670 (1988-05-01), Bahl et al.
patent: 4780906 (1988-10-01), Rajasekaran et al.
patent: 4803729 (1989-02-01), Baker
patent: 4820059 (1989-04-01), Miller et al.
patent: 4905287 (1990-02-01), Segawa
patent: 4908865 (1990-03-01), Doddington et al.
patent: 4924518 (1990-05-01), Ukita
patent: 4937871 (1990-06-01), Hattori
patent: 4987596 (1991-01-01), Ukita
patent: 5027408 (1991-06-01), Kroeker et al.
patent: 5129001 (1992-07-01), Bahl et al.
patent: 5131043 (1992-07-01), Fujii et al.
patent: 5195167 (1993-03-01), Bahl et al.
patent: 5195168 (1993-03-01), Yong
patent: 5197113 (1993-03-01), Mumolo
patent: 5218668 (1993-06-01), Higgins et al.
patent: 5233681 (1993-08-01), Bahl et al.
patent: 5241619 (1993-08-01), Schwartz et al.
patent: 5268990 (1993-12-01), Cohen et al.
patent: 5309547 (1994-05-01), Niyada et al.
patent: 5345536 (1994-09-01), Hoshimi et al.
patent: 5349645 (1994-09-01), Zhao
patent: 5369727 (1994-11-01), Nomura et al.
patent: 5369728 (1994-11-01), Kosaka et al.
patent: 5390278 (1995-02-01), Gupta et al.
patent: 5522011 (1996-05-01), Epstein et al.
Ronald Cole, Krist Roginski and Mark Fanty, "English Alphabet Recognition With Telephone Speech".
Climent Nadeu and Biing-Hwang Juang, "Filtering of Spectral Parameters for Speech Recognition", pp. S31-24.1 -S31-24.3, 1994.
Cole, Fanty, Gopalakrishnan and Janssen, "Speaker-Independent Name Retrieval From Spellings Using a Database of 50,000 Names", pp. 325-328, 1991.
Philippe Morin, Jean-claude Junqua, "Habitable Interaction in Goal-Oriented Multimodal Dialogue Systems", pp. 1669-1672.
Hoshimi, Miyata, Kiroaka and Niyada, "Speaker Independent Speech Recognition Method Using Training Speech From a Small Number of Speakers", pp. 1-469 -1-472, 1992.
Yifan Gong and Jean-Paul Haton, "Plausibility functions in continuous speech recognition: The VINICS system", pp. 187-195, 1993.

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

Speech representation by feature-based word prototypes comprisin 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 representation by feature-based word prototypes comprisin, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech representation by feature-based word prototypes comprisin will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1840352

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