Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2004-08-18
2008-09-09
Abebe, Daniel D (Department: 2626)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S251000
Reexamination Certificate
active
07424426
ABSTRACT:
An object of the present invention is to facilitate dealing with noisy speech with varying SNR and save calculation costs by generating a speech model with a single-tree-structure and using the model for speech recognition.Every piece of noise data stored in a noise database is used under every SNR condition to calculate the distance between all noise models with the SNR conditions and the noise-added speech is clustered. Based on the result of the clustering, a single-tree-structure model space into which the noise and SNR are integrated is generated (steps S1to S5). At a noise extraction step (step S6), inputted noisy speech to be recognized is analyzed to extract a feature parameter string and the likelihoods of HMMs are compared one another to select an optimum model from the tree-structure noisy speech model space (step S7). Linear transformation is applied to the selected noisy speech model space so that the likelihood is maximized (step S8).
REFERENCES:
patent: 5983180 (1999-11-01), Robinson
patent: 6026359 (2000-02-01), Yamaguchi et al.
patent: 6266636 (2001-07-01), Kosaka et al.
patent: 6658385 (2003-12-01), Gong et al.
patent: 6668243 (2003-12-01), Odell
patent: 2004/0230420 (2004-11-01), Kadambe et al.
patent: 2000-298495 (2000-10-01), None
patent: 2002-14692 (2002-01-01), None
patent: 2002-91484 (2002-03-01), None
“Online Baysian Tree-Structured Transformation of HMMs Model Selection with optimal model selection for speaker model adaptation” Wang et al. IEEE Sep. 2001.
S. Furui, “Cepstral Analysis Technique for Automatic Speaker Verification,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-29, No. 2, pp. 254-272, Apr. 1981.
M.J.F. Gales et al., “Mean and variance adaptation within the MLLR framework,” Computer Speech and Language, pp. 240-264, 1996.
S. Nakagawa, “Speech recognition with probabilistic model,” Institute of Electronics, Information and Communication Engineers, 1988 (partial English translation provided).
Sugamura et al., “Speaker independent recognition of isolated words based on multiple reference templates in SPLIT system,” Speech Committee document, S82-64, 1982 (partial English translation provided).
Z. Zhang et al., “Effects of tree-structure clustering in noise adaptation using piecewise linear transformation,” 2002 Autumn Meeting of the Acoustical Society of Japan, pp. 29-30 (partial English translation provided).
Zhipeng Zhang et al., “A Tree Structured Clustering Method Integrating Noise and SNR for Piecewise Linear-Transformation-Based Noise Adaptation”, IEEE International Conference on Acoustics, Speech, and Signal Processing, May 17, 2004, pp. 981-984, vol. 1, Montreal, Canada, XP-002297864.
Zhipeng Zhang et al., “Tree-Structured Noise Adapted HMM Modeling for Piecewise Linear-Transformation-Based Adaptation”, EUROSPEECH, Sep. 1, 2003, pp. 669-672, Geneva, Switzerland, XP-002297865.
Zhipeng Zhang et al., Study on Tree-Structure Clustering in Noise Adaptation using Piecewise Linear Transformation, 2003 Spring Meeting of the Acoustical Society of Japan, Mar. 2003, pp. 37-38.
Furui Sadaoki
Horikoshi Tsutomu
Sugimura Toshiaki
Zhang Zhipeng
Abebe Daniel D
Sadaoki Furui and NTT DoCoMo, Inc.
LandOfFree
Noise adaptation system of speech model, noise adaptation... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Noise adaptation system of speech model, noise adaptation..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Noise adaptation system of speech model, noise adaptation... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3976600