Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1995-09-15
1998-09-08
Knepper, David D.
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704245, G10L 500
Patent
active
058060294
ABSTRACT:
Hierarchical signal bias removal (HSBR) signal conditioning uses a codebook constructed from the set of recognition models and is updated as the recognition models are modified during recognition model training. As a result, HSBR signal conditioning and recognition model training are based on the same set of recognition model parameters, which provides significant reduction in recognition error rate for the speech recognition system.
REFERENCES:
patent: 4348553 (1982-09-01), Baker et al.
patent: 4718093 (1988-01-01), Brown
patent: 4783804 (1988-11-01), Juang et al.
patent: 4926488 (1990-05-01), Nadas et al.
patent: 5125022 (1992-06-01), Hunt et al.
patent: 5127043 (1992-06-01), Hunt et al.
patent: 5148489 (1992-09-01), Brell et al.
patent: 5222146 (1993-06-01), Bahl et al.
patent: 5297194 (1994-03-01), Hunt et al.
patent: 5303299 (1994-04-01), Hunt et al.
patent: 5349645 (1994-09-01), Zhao
patent: 5579436 (1996-11-01), Chou et al.
patent: 5590242 (1996-12-01), Juang et al.
Rahim and Juang, "Signal Bias Removal for Robust Telephone Based Speech Recognition in Adverse Environments," Proceeding ICASSP '94, vol. II, 1994, pp.I-445 through I-448.
Rahim, Juang, Chou and Buhrke, "Signal Conditioning Techniques for Robust Speech Recognition," IEEE Signal Processing Letters, vol. 3, No. 4, Apr. 1996, pp. 107-109.
Furui, "Unsupervised Speaker Adaptation Method Based on Hierarchical Spectral Clustering," IEEE 1989, pp. 286-289.
Furui, "Unsupervised Speaker Adaptation Based on Hierarchical Spectral Clustering," IEEE Trans on ASSP., vol. 37, No. 12, Dec. 1989, pp. 1923-1930.
Buhrke Eric Rolfe
Chou Wu
Rahim Mazin G.
AT&T Corp
Knepper David D.
Restaino Thomas A.
LandOfFree
Signal conditioned minimum error rate training for continuous sp does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Signal conditioned minimum error rate training for continuous sp, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Signal conditioned minimum error rate training for continuous sp will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1296011