Hidden Markov models with context-sensitive observations for grapheme-to-phoneme conversion.
Kalu U. OgburekePeter CahillJulie Carson-BerndsenPublished in: INTERSPEECH (2010)
Keyphrases
- context sensitive
- hidden markov models
- grapheme to phoneme conversion
- hidden states
- natural language processing
- conditional random fields
- speech recognition
- language model
- natural language
- information retrieval
- sequential data
- multiword
- viterbi algorithm
- linear dynamical systems
- baum welch
- maximum likelihood
- expectation maximization
- data mining
- language resources