Data processing: speech signal processing – linguistics – language – Speech signal processing – For storage or transmission
Reexamination Certificate
2006-06-13
2006-06-13
Dorvil, Richemond (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
For storage or transmission
C704S228000, C704S255000, C704S256000
Reexamination Certificate
active
07062433
ABSTRACT:
A method of speech recognition with compensation is provided by modifying HMM models trained on clean speech with cepstral mean normalization. For all speech utterances the MFCC vector is calculated for the clean database. This mean MFCC vector is added to the original models. An estimate of the background noise is determined for a given speech utterance. The model mean vectors adapted to the noise are determined. The mean vector of the noisy data over the noisy speech space is determined and this is removed from model mean vectors adapted to noise to get the target model.
REFERENCES:
patent: 5537647 (1996-07-01), Hermansky et al.
patent: 5924065 (1999-07-01), Eberman et al.
patent: 6691091 (2004-02-01), Cerisara et al.
patent: 6912497 (2005-06-01), Gong
Afify et al., “A General Joint Additive and Convolutive Bias Compensation Approach Applied to Noisy Lombard Speech Recognition,” IEEE Transactions on Speech and Audio Processing, Nov. 1998, vol. 6, No. 6, pp. 524-538.
Hirsch, Hans Gunter., “Adaptation of HMMS in the Presence of Additive and Convolutional Noise,” IEEE, Apr. 1997, pp. 412-419.
Tetsuo Kosaka et al., “Instantaneous Environment Adaptation Techniques Based on Fast PMC and MAP-CMS Methods” Acoustics, Speech and Signal Processing, IEEE, pp. 789-792, 1998.
Hiroki Yamamoto et al., “Fast Speech Recognition Algorithm Under Noisy Environment Using Modified CMS-PMC and Improved IDMM+SQ” Acoustics, Speech and Signal Processing, IEEE, pp. 847-850, 1997.
M. Shozakai et al., “A Non-Iterative Model-Adaptive E-CMN/PMC Approach for Speech Recognition in Car Environments” 5thEuropean Conference on Speech Communication and Technology, Sep. 22-25, 1997, Rhodes, Greece.
Brady III W. James
Dorvil Richemond
Young Donald
LandOfFree
Method of speech recognition with compensation for both... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method of speech recognition with compensation for both..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of speech recognition with compensation for both... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3678324