Dynamic Bayesian network based speech recognition with pitch and energy as auxiliary variables.
Todd A. StephensonJ. EscofetMathew Magimai-DossHervé BourlardPublished in: NNSP (2002)
Keyphrases
- speech recognition
- auxiliary variables
- hidden markov models
- automatic speech recognition
- language model
- pattern recognition
- speech processing
- speech synthesis
- speech recognizer
- speech recognition systems
- speech recognition technology
- speech signal
- speaker identification
- bayesian networks
- noisy environments
- isolated word
- deformable models
- higher order
- machine learning
- maximum likelihood
- speech recognizers
- audio visual speech recognition