An approach to efficient generation of high-accuracy and compact error-corrective models for speech recognition.
Takanobu ObaTakaaki HoriAtsushi NakamuraPublished in: INTERSPEECH (2007)
Keyphrases
- speech recognition
- high accuracy
- hidden markov models
- pattern recognition
- acoustic models
- language model
- speech processing
- handwriting recognition
- speech recognition technology
- speech synthesis
- speech signal
- speech understanding
- speaker identification
- probabilistic model
- neural network
- speech recognition systems
- data mining
- error rate
- speech recognizer
- mixture model
- speaker independent