Word-specific acoustic models in a speech recognition system

Details Word-specific acoustic models in a speech recognition system Word-specific acoustic models in a speech recognition system

2007-09-25

2007-09-25

McFadden, Susan (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

Reexamination Certificate

active

11403680

ABSTRACT:
A speech recognizer has an acoustic model that includes word-specific models, that are specific to candidate words. The candidate words would otherwise be mapped to a series of general phones. A decoder transcribes input speech into words formed by shared phones, word-specific phones and a combination of shared word-specific phones.

REFERENCES:
patent: 4852180 (1989-07-01), Levinson
patent: 5778341 (1998-07-01), Zeljkovic
patent: 6092042 (2000-07-01), Iso
patent: 6356865 (2002-03-01), Franz et al.
patent: 6374224 (2002-04-01), Horiguchi et al.
patent: 6442524 (2002-08-01), Ecker et al.
patent: 6574597 (2003-06-01), Mohri et al.
patent: 6662158 (2003-12-01), Hon et al.
patent: 7062436 (2006-06-01), Odell et al.
patent: 7076422 (2006-07-01), Hwang
“Improvements in Spontaneous Speech Recognition” by Daben Liu, etc. at Broadcast News Transcription and Understanding Workshop, Feb. 8-11, 1998, sponsored by DARPA.
Application filed for Modeling and Processing Filled Pauses and Noises in Speech Recognition, U.S. Appl. No. 10/388,259, filed Mar. 13, 2003.
Z.Liu, J. Huang, and Y. Wang, “Classification of TV programs based on audio information using hidden Markov model,” in IEEE Workshop Multimedia Signal Processing (MMSP-98), Los Angeles, CA, Dec. 7-9, 1998, pp. 27-32. Http://citeseer.ist.psu.edu/article/liu98classification.html.
S.E.Levinson, et al., “Speaker Independent Isolated Digit Recognition Using Hidden Markov Models”, pp. 1049-1052, ICASSP 83,Boston, 1983 IEEE.

Affiliated with

Also associated with

Rating

Word-specific acoustic models in a speech recognition system does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Word-specific acoustic models in a speech recognition system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Word-specific acoustic models in a speech recognition system will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3767552