Creating hidden Markov models for fast speech by optimized clustering.
Robert FaltlhauserThilo PfauGünther RuskePublished in: EUROSPEECH (1999)
Keyphrases
- hidden markov models
- speech recognition
- automatic speech recognition
- speech signal
- phoneme recognition
- automatic speech recognition systems
- audio signals
- keyword spotting
- clustering algorithm
- speaker independent
- text recognition
- viterbi algorithm
- sequential data
- markov model
- k means
- markov models
- speech processing
- discriminative training
- visual speech recognition
- gesture recognition
- acoustic models
- sequence classification
- density estimation
- handwriting recognition
- baum welch
- sequence data
- speaker dependent
- conditional random fields
- finite state transducers
- hidden states
- hidden state
- genetic algorithm