Continuously variable duration hidden Markov models for automatic speech recognition

Computer Speech and Language

Volumn 1, Issue 1, 1986, Pages 29-45

  Levinson, S E ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

MATHEMATICAL MODELS; PROBABILITY - RANDOM PROCESSES;

HIDDEN MARKOV MODELS;

SPEECH;

EID: 0022685753     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0885-2308(86)80009-2     Document Type: Article

References (18)

1. A maximum likelihood approach to continuous speech recognition
2. The DRAGON.system—an overview
3. An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes
4. A maximization technique in the statistical analysis of probabilistic functions of Markov chains
5. Growth functions for transformations on manifolds
6. Vector quantization and Markov source models applied to speech recognition
7. Connected digit recognition using vector quantization
8. Variable duration models for speech
9. Continuous speech recognition by statistical methods
10. An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition
11. Linear predictive hidden Markov models
12. A speaker independent syntax directed connected word recognition system based on hidden Markov models and level building
13. Recognition of isolated digits using hidden Markov models with continuous mixture densities
14. Explicit modeling of state occupancy in hidden Markov models for automatic speech recognition
15. Properties of large lexicons: implications for advanced isolated word recognition systems