Modelling asynchrony in automatic speech recognition using loosely coupled hidden Markov models.
Harriet J. NockSteve J. YoungPublished in: Cogn. Sci. (2002)
Keyphrases
- hidden markov models
- loosely coupled
- multi stream
- speech recognition
- automatic speech recognition
- tightly coupled
- phoneme recognition
- speech signal
- web services
- visual speech recognition
- distributed systems
- audio signals
- gesture recognition
- markov models
- service oriented architecture
- speaker independent
- sequential data
- conditional random fields
- viterbi algorithm
- acoustic models
- markov model
- automatic speech recognition systems
- speaker identification
- visual speech
- speech recognizer
- hidden states
- video sequences
- text recognition
- hidden state
- sequence classification
- noisy environments
- speech processing
- baum welch
- keyword spotting
- text to speech
- broadcast news
- speaker dependent
- semantic web services
- audio visual
- continuous hidden markov models