Direct training of subspace distribution clustering hidden Markov model

IEEE Transactions on Speech and Audio Processing

Volumn 9, Issue 4, 2001, Pages 378-387

  Mak, Brian Kan Wing ^a,b   Bocchieri, Enrico ^c  

^a IEEE   (Hong Kong)

^b HONG KONG UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Hong Kong)

^c AT AND T LABS RESEARCH   (United States)

Author keywords

Direct training; Subspace distribution clustering hidden Markorv modeling; Subspace distribution tying structure

Indexed keywords

ACOUSTIC MODELS; AUTOMATIC SPEECH RECOGNITION (ASR);

ACOUSTIC SIGNAL PROCESSING; LEARNING ALGORITHMS; MARKOV PROCESSES; NEURAL NETWORKS; VOCABULARY CONTROL;

SPEECH RECOGNITION;

EID: 0035339805     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.917683     Document Type: Article

References (17)

1. Subspace distribution clustering for continuous observation density hidden Markov models
2. Stream derivation and clustering schemes for subspace distribution clustering HMM
3. State tying of triphone HMM's for the 1994 AT&T ARPA ATIS recognizer
4. The SPHINX-II speech recognition system: An overview
5. Multi-site data collection and evaluation in spoken language understanding
6. A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains
7. Maximum likelihood estimation for multivariate mixture observations of Markov chains
8. Expanding the scope of the ATIS task: The ATIS-3 corpus
9. The 1994 AT&T ATIS CHRONUS recognizer
10. A segmental K-means algorithm for estimating parameters of hidden Markov models
11. The design for the wall street journal-based CSR corpus
12. A discriminant measure for model complexity adaptation
13. Clustering via the Bayesian information criterion with applications in speech recognition
14. Recent improvements to IBM's speech recognition system for automatic speech recognition