Efficient data selection for speech recognition based on prior confidence estimation using speech and monophone models.
Satoshi KobashikawaTaichi AsamiYoshikazu YamaguchiHirokazu MasatakiSatoshi TakahashiPublished in: Comput. Speech Lang. (2014)
Keyphrases
- speech recognition
- speech synthesis
- speech signal
- speech recognizer
- hidden markov models
- speech processing
- automatic speech recognition
- language model
- training data
- speech recognition systems
- noisy environments
- pattern recognition
- speaker dependent
- speaker identification
- visual data
- probabilistic model
- neural network
- acoustic models