Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition.
Paul R. DixonTasuku OonishiSadaoki FuruiPublished in: Comput. Speech Lang. (2009)
Keyphrases
- speech recognition
- speech recognition systems
- graphics processors
- speaker independent
- speech recognizers
- acoustic models
- speech recognizer
- hidden markov models
- speech signal
- language model
- speech synthesis
- pattern recognition
- noisy environments
- automatic speech recognition
- noisy speech
- speech processing
- speaker identification
- speaker dependent
- speech retrieval
- speech recognition technology
- acoustic features
- gpu implementation
- maximum likelihood
- general purpose
- neural network
- isolated word