Decoding multiple HMM sets using a single sentence grammar

Details Decoding multiple HMM sets using a single sentence grammar Decoding multiple HMM sets using a single sentence grammar

2007-09-11

2007-09-11

Chawan, Vijay (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S256000, C704S240000, C704S231000

Reexamination Certificate

active

09915911

ABSTRACT:
For a given sentence grammar, speech recognizers are often required to decode M sets of HMMs each of which models a specific acoustic environment. In order to match input acoustic observations to each of the environments, typically recognition search methods require a network of M sub-networks. A new speech recognition search method is described here, which needs that is only the size of a single sub-network and yet gives the same recognition performance, thus reducing memory requirement for network storage by (M−1)/M.

REFERENCES:
patent: 5333275 (1994-07-01), Wheatley et al.
patent: 5806034 (1998-09-01), Naylor et al.
patent: 5819221 (1998-10-01), Kondo et al.
patent: 6055498 (2000-04-01), Neumeyer et al.
patent: 6076057 (2000-06-01), Narayanan et al.
patent: 6226611 (2001-05-01), Neumeyer et al.
patent: 6285981 (2001-09-01), Kao
Imperl, Bojan: “Multilingual Connected Digits and Naural Numbers Recognition in the Telephone Speech Dialog Systems”; Proceedings of the IEEE International Symposium on Industrial Electronics; Jul. 1999, pp. 188-189.
Korkmazskiy, Filipp et al.; “Generalized Mixture of HMMS for Continuous Speech Recognition”; 1997 IEEE International Conference on Acoustics, Speech and Signal Processing; Apr. 1997, pp. 1443-1446.
Gong, Yifan et al.; “Parallel Construction of Syntactic Structure for Continuous Speech Recognition”, Proceedings of the European Conference on Speech Communication and Technology, Sep. 1989, pp. 47-50.

Affiliated with

Also associated with

Rating

Decoding multiple HMM sets using a single sentence grammar does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Decoding multiple HMM sets using a single sentence grammar, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Decoding multiple HMM sets using a single sentence grammar will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3722457