State-dependent phonetic tied mixtures with pronunciation modeling for spontaneous speech recognition.
Yi LiuPascale FungPublished in: IEEE Trans. Speech Audio Process. (2004)
Keyphrases
- speech recognition
- state dependent
- speaker independent
- hidden markov models
- language model
- automatic speech recognition
- speech signal
- steady state
- speech recognizer
- speaker identification
- speech recognition technology
- speech synthesis
- speech processing
- pattern recognition
- arrival rate
- speaker dependent
- noisy environments
- queue length
- queueing networks
- optimal policy
- mixture model
- conversational speech
- asymptotically optimal
- speech retrieval
- neural network
- stationary distribution
- acoustic models
- single server
- natural language processing
- bayesian networks
- image processing
- computer vision