Adaptation of Hidden Markov Models for Recognizing Speech of Reduced Frame Rate.
Lee-Min LeeFu-Rong JeanPublished in: IEEE Trans. Cybern. (2013)
Keyphrases
- hidden markov models
- frame rate
- speech recognition
- speech signal
- automatic speech recognition
- speaker adaptation
- phoneme recognition
- video sequences
- high speed
- text recognition
- speaker independent
- automatic speech recognition systems
- speech recognizer
- video camera
- keyword spotting
- hidden state
- markov models
- visual speech
- speaker identification
- dynamic scenes
- video quality
- viterbi algorithm
- sequential data
- d scene
- gesture recognition
- visual speech recognition
- hidden states
- continuous hidden markov models
- acoustic models
- audio signals
- speaker dependent
- noisy environments
- sequence classification
- broadcast news
- real time
- acoustic features
- space time
- maximum likelihood
- multiresolution
- reinforcement learning
- high quality
- image processing