Exploiting sparsity in stranded hidden Markov models for automatic speech recognition.
Yong ZhaoBiing-Hwang JuangPublished in: ACSCC (2012)
Keyphrases
- automatic speech recognition
- hidden markov models
- speech recognition
- broadcast news
- conversational speech
- speech signal
- sequential data
- speech retrieval
- gesture recognition
- markov model
- markov models
- speech corpus
- noisy environments
- discriminative training
- conditional random fields
- pattern recognition
- hidden state
- sequence classification
- image processing
- viterbi algorithm
- word recognition
- sparse representation
- acoustic features
- protein sequences
- hidden states
- visual speech recognition
- higher order
- machine learning
- continuous hidden markov models