Speech and signal digitization by using recognition metrics...

Details Speech and signal digitization by using recognition metrics... Speech and signal digitization by using recognition metrics...

2006-03-21

2006-03-21

Armstrong, Angela (Department: 2654)

Data processing: speech signal processing, linguistics, language

Speech signal processing

Recognition

C704S236000

Reexamination Certificate

active

07016835

ABSTRACT:
A characteristic-specific digitization method and apparatus are disclosed that reduces the error rate in converting input information into a computer-readable format. The input information is analyzed and subsets of the input information are classified according to whether the input information exhibits a specific physical parameter affecting recognition accuracy. If the input information exhibits the specific physical parameter affecting recognition accuracy, the characteristic-specific digitization system recognizes the input information using a characteristic-specific recognizer that demonstrates improved performance for the given physical parameter. If the input information does not exhibit the specific physical parameter affecting recognition accuracy, the characteristic-specific digitization system recognizes the input information using a general recognizer that performs well for typical input information. In one implementation, input speech having very low recognition accuracy as a result of a physical speech characteristic is automatically identified and recognized using a characteristic-specific speech recognizer.

REFERENCES:
patent: 4654875 (1987-03-01), Srihari et al.
patent: 4763278 (1988-08-01), Rajasekaran et al.
patent: 4994983 (1991-02-01), Landell et al.
patent: 5157384 (1992-10-01), Greanias et al.
patent: 5298674 (1994-03-01), Yun
patent: 5319736 (1994-06-01), Hunt
patent: 5586180 (1996-12-01), Degenhardt et al.
patent: 5687288 (1997-11-01), Dobler et al.
patent: 5712957 (1998-01-01), Waibel et al.
patent: 5729655 (1998-03-01), Kolesnik et al.
patent: 5751903 (1998-05-01), Swaminathan et al.
patent: 5758002 (1998-05-01), Trompf et al.
patent: 5774857 (1998-06-01), Newlin
patent: 5774858 (1998-06-01), Taubkin et al.
patent: 5835607 (1998-11-01), Martin et al.
patent: 5842168 (1998-11-01), Miyazawa et al.
patent: 5864804 (1999-01-01), Kalveram
patent: 5960397 (1999-09-01), Rahim
patent: 6044344 (2000-03-01), Kanevsky
patent: 6058359 (2000-05-01), Hagen et al.
patent: 6067517 (2000-05-01), Bahl et al.
patent: 6073097 (2000-06-01), Gould et al.
patent: 6104321 (2000-08-01), Akagiri
patent: 6122613 (2000-09-01), Baker
patent: 6151576 (2000-11-01), Warnock et al.
patent: 6233553 (2001-05-01), Contolini et al.
patent: 6233559 (2001-05-01), Balakrishnan
patent: 6243713 (2001-06-01), Nelson et al.
patent: 6285786 (2001-09-01), Seni et al.
patent: 6345252 (2002-02-01), Beigi et al.
patent: 6535287 (2003-03-01), Matsui et al.
patent: 6618702 (2003-09-01), Kohler et al.
patent: 2003/0004714 (2003-01-01), Kanevsky et al.
patent: 08-248988 (1996-09-01), None
patent: 10-164638 (1998-06-01), None
patent: 2001-356790 (2001-12-01), None
Fiscus (A Post-Processing System To Yield Reduced Word Error Rates: Recognizer Output Voting Error Reduction (ROVER) IEEE Workshop on Automatic Speech Recognition and Understanding, Dec. 1997).
Siegler, M.A., “Measuring and Compensating for the Effects of Speech Rate in Large Vocabulary Continuous Speech Recognition,” Carnegie Mellon University (Dec. 1995).
Nalwa, V.S., “Automatic On-Line Signature Verification,” Proceedings of IEEE, 215-239 (Feb. 1997).
Bahl et al., “A Method for the Construction of Acoustic Markov Models for Words,” RC 13099 (#58580) Computer Science, 13 pages (Sep. 1987).

Affiliated with

Also associated with

Rating

Speech and signal digitization by using recognition metrics... 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 and signal digitization by using recognition metrics..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Speech and signal digitization by using recognition metrics... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3603309