Speech recognition utilizing multitude of speech features

Details Speech recognition utilizing multitude of speech features Speech recognition utilizing multitude of speech features

2003-11-28

2008-12-09

Wozniak, James S (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S240000, C704S251000

Reexamination Certificate

active

07464031

ABSTRACT:
In a speech recognition system, the combination of a log-linear model with a multitude of speech features is provided to recognize unknown speech utterances. The speech recognition system models the posterior probability of linguistic units relevant to speech recognition using a log-linear model. The posterior model captures the probability of the linguistic unit given the observed speech features and the parameters of the posterior model. The posterior model may be determined using the probability of the word sequence hypotheses given a multitude of speech features. Log-linear models are used with features derived from sparse or incomplete data. The speech features that are utilized may include asynchronous, overlapping, and statistically non-independent speech features. Not all features used in training need to appear in testing/recognition.

REFERENCES:
patent: 6304841 (2001-10-01), Berger et al.
patent: 6456969 (2002-09-01), Beyerlein
patent: 7054810 (2006-05-01), Gao et al.
patent: 7324927 (2008-01-01), Weng et al.
patent: 2003/0023438 (2003-01-01), Schramm et al.
patent: PUPA 07-56595 (1995-03-01), None
patent: PUPA 2001-511267 (2001-08-01), None
patent: PUPA 2003-022088 (2003-01-01), None
Vergyri. “Integration of Multiple Knowledge Sources in Speech Recognition Using Minimum Error Training.” PhD Thesis, Johns Hopkins University, 2000.
Byrne et al, “Towards Language Independent Acoustic Modeling”, IEEE Workshop on Automatic Speech Recognition and Understanding, 1999.
Shimodaira. “A new criterion for selecting models from partially observed data.” In: Cheeseman, P., Oldford, R.W. (Eds.), Selecting Models from Data: AI and Statistics IV. Springer, Berlin, 1994, pp. 21-30.
Kirchhoff, “Combining articulatory and acoustic information for speech recognition in noisy and reverberant environ-ments,” Proc. Int. Conf. on Spoken Language Proc., 1998, pp. 891-894.
P. Beyerlein, “Discriminative Model Combination”, 1997 IEEE, p. 238-245.
D. Vergyri, “Use of Word Level Side Information to Improve Speech Recognition”, 2000 IEEE, vol. 3, p. 1823-1826.

Affiliated with

Also associated with

Rating

Speech recognition utilizing multitude of speech features 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 utilizing multitude of speech features, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition utilizing multitude of speech features will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4023198