Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Patent
1997-05-02
1998-08-11
Dorvil, Richemond
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
704249, G10L 506
Patent
active
057941971
ABSTRACT:
A speech recognition method provides improved modeling in recognition accuracy using hidden Markov models. During training, the method creates a senone tree for each state of each phoneme encountered in a data set of training words. All output distributions received for a selected state of a selected phoneme in the set of training words are clustered together in a root node of a senone tree. Each node of the tree beginning with the root node is divided into two nodes by asking linguistic questions regarding the phonemes immediately to the left and right of a central phoneme of a triphone. At a predetermined point, the tree creation stops, resulting in leaves representing clustered output distributions known as senones. The senone trees allow all possible triphones to be mapped into a sequence of senones simply by traversing the senone trees associated with the central phoneme of the triphone. As a result, unseen triphones not encountered in the training data can be modeled with senones created using the triphones actually found in the training data.
REFERENCES:
patent: 4783803 (1988-11-01), Baker et al.
patent: 4817156 (1989-03-01), Bahl et al.
patent: 4829577 (1989-05-01), Kuroda et al.
patent: 4829578 (1989-05-01), Roberts
patent: 4866778 (1989-09-01), Baker
patent: 5027406 (1991-06-01), Roberts et al.
patent: 5033087 (1991-07-01), Bahl et al.
patent: 5054074 (1991-10-01), Bakis
patent: 5440663 (1995-08-01), Moese et al.
Bahl et al., "Decision Trees for Phonological Rules in Continuous Speech," IEEE International Conference on Acoustics, Speech, and Signal Processing, 1991, pp. 185-188. Apr. 1991.
Hon et al., "CMU Robust Vocabulary-Independent Speech Recognition System," IEEE International Conference on Acoustics, Speech, and Signal Processing, 1991, pp. 889-892. Apr. 1991.
Takami and Sagayama, "A Successive State Splitting Algorithm for Efficient Allophone Modeling," IEEE, 1992, pp. I-573-576. Mar. 1992.
Hwang et al., "Predicting Unseen Triphones with Senones," paper delivered at DARPA Workshop on Speech Recognition, Jan. 20, 1993.
Hwang and Huang, Acoustic Classification of Phonetic Hidden Markov Models, in Proceedings of 2nd European Conference on Speech and Communication and Technology 2:785-788, Genova, Italy, Sep. 24-26, 1991.
Lee, "Context Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech Recognition," IEEE Transactions on Acoustics, Speech, And Signal Processing 38(4):599-609, Apr. 4, 1990.
Improved Vocabulary-Independent Sub-Word HMM Modeling Wood et al, ICASSP '91. 1991 International Conf. on Acoustics, . . . /14-17 May 91, pp. 181-184.
Hwang et al., "Subphonetic Modeling With Markov States-Senone" ICASSP 92. 1992 International Conf. on Acoustics, . . . /23-26 Mar. 92, pp. I-33 to I-36.
Hwang et al., Predicting Unseen Triphones with senones ICASSP 93. 1993 International Conf. on Acoustics, . . . /27-30 Apr. 9, pp. II-311 to II314 .
Alleva Fileno A.
Huang Xuedong
Hwang Mei-Yuh
Dorvil Richemond
Micrsoft Corporation
LandOfFree
Senone tree representation and evaluation does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Senone tree representation and evaluation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Senone tree representation and evaluation will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-403589