Speech to talking heads system based on hidden Markov models.
Tatsuo YotsukuraShigeo MorishimaSatoshi NakamuraPublished in: SIGGRAPH Posters (2005)
Keyphrases
- hidden markov models
- speech recognition
- speech signal
- automatic speech recognition
- phoneme recognition
- speaker independent
- text recognition
- automatic speech recognition systems
- sequential data
- keyword spotting
- speech recognizer
- markov models
- acoustic models
- visual speech
- conditional random fields
- baum welch
- audio signals
- speech processing
- noisy environments
- gesture recognition
- discriminative training
- sequence classification
- viterbi algorithm
- speaker identification
- speech recognition systems
- higher order
- text to speech
- markov model
- hidden states
- broadcast news
- visual speech recognition