Methods for reducing spurious insertions in speech recognition

Details Methods for reducing spurious insertions in speech recognition Methods for reducing spurious insertions in speech recognition

2003-04-04

2008-08-05

Azad, Abul (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

Reexamination Certificate

active

07409345

ABSTRACT:
Techniques for improving an automatic baseform generation system. More particularly, the invention provides techniques for reducing insertion of spurious speech events in a word or phone sequence generated by an automatic baseform generation system. Such automatic baseform generation techniques may be accomplished by enhancing the scores of long-lasting speech events with respect to the scores of short-lasting events. For example, this may be achieved by merging competing candidates that relate to the same speech event (e.g., phone or word) and that overlap in time into a single candidate, the score of which may be equal to the sum of the scores of the merged candidates.

REFERENCES:
patent: 4833712 (1989-05-01), Bahl et al.
patent: 5729656 (1998-03-01), Nahamoo et al.
patent: 5799276 (1998-08-01), Komissarchik et al.
patent: 6260014 (2001-07-01), Bahl et al.
patent: 7054810 (2006-05-01), Gao et al.
patent: 7181395 (2007-02-01), Deligne et al.
U.S. Appl. No. 09/698,470, filed Oct. 27, 2000, “Methods and Apparatus for Automatic Generation of Multiple Pronunciations from Acoustic Data.”
R.C. Rose et al., “Speech Recognition Using Automatically Derived Baseforms,” ICASSP, pp. 1271-1274, 1997.
B. Ramabhadran et al., Acoustics-Only Based Automatic Phonetic Baseform Generation, ICASSP, 4 pages, 1998.
B. Ramabhadran et al., “Phonological Rules for Enhancing Acoustic Enrollment of Unknown Words,” ICASLP '98, 4 pages, 1998.
L.E. Baum et al., “A Maximization Technique Occuring in the Statistical Analysis of Probabilistic Functions of Markov Chains,” vol. 41, No. 1, pp. 164-171, 1970.
S. Deligne et al., “Automatic Generation and Selection of Multiple Pronunciations for Dynamic Vocabularies,” ICASSP, 4 pages, 2001.
L. Rabiner and B.H. Juang, “Signal Processing and Analysis Methods for Speech Recognition,” Prentice Hall Signal Processing Series, Chapter 3, pp. 69-117, 1993.

Affiliated with

Also associated with

Rating

Methods for reducing spurious insertions in speech recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Methods for reducing spurious insertions in speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Methods for reducing spurious insertions in speech recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4016475