Dynamic N-best algorithm to reduce recognition errors

Details Dynamic N-best algorithm to reduce recognition errors Dynamic N-best algorithm to reduce recognition errors

2004-05-18

2008-09-02

Vo, Huyen X. (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

C704S247000, C704S240000

Reexamination Certificate

active

07421387

ABSTRACT:
A method for reducing recognition errors. The method includes receiving an N-best list associated with an input of a computer based recognition system. The N-best list includes one or more hypotheses and associated confidence values. The input is classified in response to the N-best list, resulting in a classification. A re-scoring algorithm that is tuned for the classification is selected. The re-scoring algorithm is applied to the N-best list to create a re-scored N-best list. A hypothesis for the value of the input is selected based on the re-scored N-best list.

REFERENCES:
patent: 5241619 (1993-08-01), Schwartz et al.
patent: 5712957 (1998-01-01), Waibel et al.
patent: 6587818 (2003-07-01), Kanevsky et al.
patent: 6587824 (2003-07-01), Everhart et al.
patent: 6757652 (2004-06-01), Lund et al.
patent: 2002/0173955 (2002-11-01), Reich
patent: 2003/0125948 (2003-07-01), Lyudovyk
patent: 2003/0139924 (2003-07-01), Balasuriya

Affiliated with

Also associated with

Rating

Dynamic N-best algorithm to reduce recognition errors does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Dynamic N-best algorithm to reduce recognition errors, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dynamic N-best algorithm to reduce recognition errors will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3991444