Modeling acoustic transitions in speech by state-interpolation hidden Markov models.
Li DengPatrick KennyMatthew LennigPaul MermelsteinPublished in: IEEE Trans. Signal Process. (1992)
Keyphrases
- hidden markov models
- speech recognition
- state transition
- speaker independent
- noisy speech
- hidden states
- acoustic models
- automatic speech recognition
- speech signal
- hidden state
- phoneme recognition
- visual speech
- speech recognition systems
- linear dynamical systems
- audio signals
- text recognition
- automatic speech recognition systems
- markov models
- markov model
- speaker dependent
- visual speech recognition
- keyword spotting
- viterbi algorithm
- gesture recognition
- conditional random fields
- acoustic features
- random effects
- speech recognizer
- continuous hidden markov models
- speech processing
- noisy environments
- handwritten text recognition
- speaker identification
- state space