Integrated speech recognition and semantic classification

Details Integrated speech recognition and semantic classification Integrated speech recognition and semantic classification

2007-01-19

2010-12-21

Chawan, Vijay B (Department: 2626)

Data processing: speech signal processing, linguistics, language

Linguistics

Natural language

C704S257000, C704S256200, C704S004000, C704S251000, C704S260000

Reexamination Certificate

active

07856351

ABSTRACT:
A novel system integrates speech recognition and semantic classification, so that acoustic scores in a speech recognizer that accepts spoken utterances may be taken into account when training both language models and semantic classification models. For example, a joint association score may be defined that is indicative of a correspondence of a semantic class and a word sequence for an acoustic signal. The joint association score may incorporate parameters such as weighting parameters for signal-to-class modeling of the acoustic signal, language model parameters and scores, and acoustic model parameters and scores. The parameters may be revised to raise the joint association score of a target word sequence with a target semantic class relative to the joint association score of a competitor word sequence with the target semantic class. The parameters may be designed so that the semantic classification errors in the training data are minimized.

REFERENCES:
patent: 5477451 (1995-12-01), Brown et al.
patent: 5805832 (1998-09-01), Brown et al.
patent: 5828999 (1998-10-01), Bellegarda et al.
patent: 5991710 (1999-11-01), Papineni et al.
patent: 6157912 (2000-12-01), Kneser et al.
patent: 6490555 (2002-12-01), Yegnanarayanan et al.
patent: 6567778 (2003-05-01), Chao Chang et al.
patent: 6856956 (2005-02-01), Thrasher et al.
patent: 6920420 (2005-07-01), Lin
patent: 7016830 (2006-03-01), Huang et al.
patent: 7191132 (2007-03-01), Brittan et al.
patent: 7249012 (2007-07-01), Moore
patent: 2002/0042711 (2002-04-01), Lin
patent: 2004/0049375 (2004-03-01), Brittan et al.
patent: 2004/0098247 (2004-05-01), Moore
patent: 2004/0220809 (2004-11-01), Wang et al.
patent: 2004/0249628 (2004-12-01), Chelba et al.
patent: 2005/0033574 (2005-02-01), Kim et al.
patent: 2005/0065789 (2005-03-01), Yacoub et al.
patent: 2005/0080611 (2005-04-01), Huang et al.
patent: 2005/0080615 (2005-04-01), Huang et al.
patent: 2005/0228641 (2005-10-01), Chelba et al.
patent: 2005/0228649 (2005-10-01), Harb et al.
patent: 2006/0004570 (2006-01-01), Ju et al.
patent: 2006/0069678 (2006-03-01), Chou et al.
patent: 2006/0195321 (2006-08-01), Deligne et al.
patent: 2007/0100624 (2007-05-01), Weng et al.
patent: 2007/0143101 (2007-06-01), Goutte
patent: 2008/0113801 (2008-05-01), Moreno
patent: 0562138 (1992-03-01), None
patent: WO0133551 (2001-05-01), None
patent: 2010029783 (2010-05-01), None
Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error; Erik McDermott, Timothy J. Hazen, Jonathan Le Roux, Atsushi Nakamura and Shigeru Katagiri; IEEE Transactions on Audio, Speech, and Language Processing; 1558-7916; 2006 IEEE.
Discriminative Models for Spoken Language Understanding; Ye-Yi Wang and Alex Acero; Microsoft Research, Redmond, Washington, USA, Sep. 2006.
Minimum Classification Error Rate Methods for Speech Recognition; Biing-Hwang Juang, Wu Chou and Chin-Hui Lee; IEEE Transactions on Speech and Audio Processing, vol. 5, No. 3, May 1997.
Discriminative Learning for Minimum Error Classification; Biing-Hwang Juang and Shigeru Katagiri; IEEE Transactions on Signal Processing, vol. 40, No. 12, Dec. 1992.
PCT/US2008/051584 PCT International Search Report and Written Opinion dated mailed Jun. 23, 2008.
Ye-Yi Wang et al., “Speech Utterance Classification Model Training without Manual Transcriptions” In: 2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006, May 14, 2006, vol. 1, pp. 553-556.
W. Chou “Discriminant-Function-Based Minimum Recognition Error Rate Pattern-Recognition Approach to Speech Recognition” In: Processing of the IEEE, Aug. 2000, vol. 88, No. 8, pp. 1201-1223.

Affiliated with

Also associated with

Rating

Integrated speech recognition and semantic classification does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Integrated speech recognition and semantic classification, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Integrated speech recognition and semantic classification will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4226122