Speech recognition accuracy with multi-confidence thresholds

Details Speech recognition accuracy with multi-confidence thresholds Speech recognition accuracy with multi-confidence thresholds

2006-09-08

2010-02-02

Vo, Huyen X. (Department: 2626)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S236000, C704S245000

Reexamination Certificate

active

07657433

ABSTRACT:
A speech recognition system uses multiple confidence thresholds to improve the quality of speech recognition results. The choice of which confidence threshold to use for a particular utterance may be based on one or more features relating to the utterance. In one particular implementation, the speech recognition system includes a speech recognition engine that provides speech recognition results and a confidence score for an input utterance. The system also includes a threshold selection component that determines, based on the received input utterance, a threshold value corresponding to the input utterance. The system further includes a threshold component that accepts the recognition results based on a comparison of the confidence score to the threshold value.

REFERENCES:
patent: 6473735 (2002-10-01), Wu et al.
patent: 6850886 (2005-02-01), Abrego et al.
patent: 7103542 (2006-09-01), Doyle
patent: H2187 (2007-04-01), Yuchimiuk
“National Institute of Standard arid Technology (NIST) SCLItc—speech recognition scoring program,” http://www.nlst.gov/speech/tools/index.html [Aug. 9, 2007].
Chang, Shuangyu, “Improving Speech Recognition Accuracy with Multi Confidence Thresholding,” Interspeech 2006, ICSLP Ninth International Conference on Spoken Language Processing, Pittsburgh, PA, USA, Sep. 17-21, 2006, 5 pages.
Chen, Z. and Ding, X., “Rejection Algorithm for Mis-segmented Characters in Multilingual Document Recognition,” In Proceedings of 7th Intl. Conf. on Doc. Analysis and Recognition, vol. 2, 2003, 4 pages.
Gunawardana, A., I-Ion, H. And Jiang, L. “Word-Based Acoustic Confidence Measures for Large-Vocabulary Speech Recognition,” In Proceeding of ICSLP98, 1998, 4 pages.
Gupta, S. and Soong, F., “Improved Utterance Rejection Using Length Dependent Thresholds,” 117 Proceedings of ICSLP98, Sydney, 1998.
Wessel, F., Schluter, Macherey, K. and Ney, H., “Confidence Measures for Large Vocabulary Continuous Speech Recognition,” In IEEE Trans. Speech and Audio Processing, vol. 9, No. 3, Mar. 2001, pp. 288-298.
Williams, D. A., “Knowing What You Don't Know: Roles for Confidence Measures in Automatic Speech Recognition,” Ph.D. Dissertation, University of Sheffield, May 1999, 123 pages.

Affiliated with

Also associated with

Rating

Speech recognition accuracy with multi-confidence thresholds 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 accuracy with multi-confidence thresholds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech recognition accuracy with multi-confidence thresholds will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4165341