N-best list rescoring in speech recognition

Details N-best list rescoring in speech recognition N-best list rescoring in speech recognition

2005-12-16

2010-06-29

Hudspeth, David R (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S009000, C704S252000, C715S767000

Reexamination Certificate

active

07747437

ABSTRACT:
A method of speech recognition processing is described based on an N-best list of recognition hypotheses corresponding to a spoken input. Each hypothesis on the N-best list is rescored based on its rank in the rescored N-best list. The rescoring may be based on a Statistical Language Model (SLM) or Dynamic Semantic Model (DSM). One or more rescoring categories may be associated with each recognition hypotheses to affect or bias the rescoring.

REFERENCES:
patent: 5241619 (1993-08-01), Schwartz et al.
patent: 5745649 (1998-04-01), Lubensky
patent: 2002/0133341 (2002-09-01), Gillick et al.
patent: 2002/0135618 (2002-09-01), Maes et al.
patent: 2002/0150295 (2002-10-01), Kwok et al.
patent: 2005/0187768 (2005-08-01), Godden
patent: 2006/0009974 (2006-01-01), Junqua et al.
patent: 2006/0190256 (2006-08-01), Stephanick et al.
Schwartz et al., ‘New uses for the N-Best sentence hypotheses within the BYBLOS speech recognition system’, 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing, 1992. ICASSP-92., vol. 1, pp. 1-4.
Pellom et al., ‘University of Colorado Dialog Systems for Travel and Navigation’, Proceedings of the first international conference on Human language technology research, San Diego, 2001, pp. 1-6.
Wai et al. “A Dynamic Semantic Model for Re-scoring Recognition Hypotheses”, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01)., published Aug. 7, 2002, vol. 1, 589-592.
Stolcke, Andreas, ‘SRILM An Extensible Language Modeling Toolkit’ (2002).
Wang et al., ‘Rescoring effectiveness of language models using different levels of knowledge and their integration’, IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002. Proceedings. (ICASSP '02)., vol. 1, pp. I-785-I-788.

Affiliated with

Also associated with

Rating

N-best list rescoring 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 N-best list rescoring in speech recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and N-best list rescoring in speech recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4245280