Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
2005-08-16
2005-08-16
Chawan, Vijay (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S256000, C704S252000, C704S232000
Reexamination Certificate
active
06931374
ABSTRACT:
A method is developed which includes 1) defining a switching state space model for a continuous valued hidden production-related parameter and the observed speech acoustics, and 2) approximating a posterior probability that provides the likelihood of a sequence of the hidden production-related parameters and a sequence of speech units based on a sequence of observed input values. In approximating the posterior probability, the boundaries of the speech units are not fixed but are optimally determined. Under one embodiment, a mixture of Gaussian approximation is used. In another embodiment, an HMM posterior approximation is used.
REFERENCES:
patent: 5317673 (1994-05-01), Cohen et al.
patent: 5692097 (1997-11-01), Yamada et al.
patent: 5799272 (1998-08-01), Zhu
patent: 5924066 (1999-07-01), Kundu
patent: 6591146 (2003-07-01), Pavlovic et al.
patent: 6678658 (2004-01-01), Hogden et al.
patent: 2003/0187642 (2003-10-01), Ponceleon et al.
Merhav et al (“Maximum Likelihood Hidden Markov Modeling Using A Dominant Sequence Of States”, IEEE Transactions on Signal Processing, Sep. 1991).
Merhav et al (“Hidden Markov Modeling Using The Most Likely State Sequence”, International Conference on Acoustics, Speech, and Signal Processing, Apr. 1991).
Bourlard et al (“A Training Algorithm For Statistical Sequence Recognition With Applications To Transition-Based Speech Recognition”, IEEE Signal Processing Letters, Jul. 1996).
Zhou et al (Coarticulation Modeling by Embedding a Target-Directed Hidden Trajectory Model into HMM—Model and Training Microsoft Research Paper http://research.microsoft.com/srg/papers/2003-zhou-icassp.pdf, Jan. 2003).
L. Deng, “A Dynamic, Feature-Based Approach to the Interface Between Phonology and Phonetics for Speech Modeling and Recognition,” Speech Communication, vol. 24, No. 4, pp. 299-323 (1998).
L. Deng and Z. Ma, “Spontaneous Speech Recognition Using A Statistical Coarticulatory Model for the Hidden Vocal-Tract-Resonance Dynamics,” J. Acoust. Soc. Am., vol. 108, No. 6, pp. 3036-3048 (2000).
L. Deng and J. Ma, “A Statistical Coarticulatory Model for the Hidden Vocal-Tract-Resonance Dynamics,” Proc. of Eurospeech, vol. 4, pp. 1499-1502 (Sep. 1999).
L. Deng and H. Sameti, “Transitional Speech Units and Their Representation by the Regressive Markov States: Applications to Speech Recognition,” IEEE Trans. Speech Audio Proc., vol. 4, No. 4, pp. 301-306 (Jul. 1996).
L. Deng and D. Sun, “A Statistical Approach to Automatic Speech Recognition Using the Atomic Speech Units Constructed from Overlapping Articulatory Features,” J. Acoust. Soc. Am., vol. 95, pp. 2702-2719 (1994).
Y. Gao et al., “Multistage Coarticulation Model Combining Articulatory, Formant and Cepstral Features,” Poc. ICSLP. vol. 1, pp. 25-28 (2000).
J. Ma and L. Deng, “A Path-Stack Algorithm for Optimizing Dymanic Regimes in a Statistical Hidden Dynamic Model of Speech,” Computer Speech and Language, vol. 14, pp. 101-104 (2000).
M. Ostendorf et al., “From HMMs to Segment Models: A Unified View of Stochastic Modeling for Speech Recognition,” IEEE Trans. Speech Audio Proc., vol. 4, pp. 360-378 (1996).
J. Ma and J. Deng, “Target-Directed Mixture Linear Dynamic Models for Spontaneous Speech Recognition,” IEEE Trans. Speech and Audio Processing (submitted 1999, to appear 2002).
J. Bridle et al., “An Investigation of Segmental Hidden Dynamic Models of Speech Coarticulation for ASR,” http://www.clsp.jhu.edu/ws98/projects/dynamic/presentations/finalhtml/index.html, Johns Hopkins Univ. 1998).
F.-L. Chen et al., “The Structure and Its Implementation of Hidden Dynamic HMM for Mandarin Speech Recognition,” Proc. ICSLP, pp. 713-716, Denver (2002).
Attias Hagai
Deng Li
Lee Leo Jingyu
Chawan Vijay
Magee Theodore M.
Microsoft Corporation
Westman Champlin & Kelly P.A.
LandOfFree
Method of speech recognition using variational inference... 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 using variational inference..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of speech recognition using variational inference... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3479757