Phoneme recognition in various styles of utterance based on mutual information criterion.
Shigeki OkawaTetsunori KobayashiKatsuhiko ShiraiPublished in: ICSLP (1994)
Keyphrases
- information criterion
- phoneme recognition
- speech recognition
- speaker dependent
- hidden markov models
- cross validation
- model selection
- automatic speech recognition
- probability model
- bayesian information criterion
- speaker independent
- factor analysis
- speaker identification
- widely applicable
- leave one out cross validation
- spoken language
- audio signal
- sample size
- speech signal
- free energy
- pattern recognition
- face recognition
- bayesian networks
- data sets
- learning theory
- upper bound