Inversion-based nonlinear adaptation of noisy acoustic parameters for a neural/HMM speech recognizer.
Edmondo TrentinMarco GoriPublished in: Neurocomputing (2006)
Keyphrases
- speech recognizer
- speech recognition
- speaker adaptation
- speaker independent
- speech recognizers
- maximum likelihood
- speech recognition systems
- acoustic models
- hidden markov models
- noisy environments
- speech understanding
- spoken language
- broadcast news
- speech signal
- neural network
- language model
- pattern recognition
- semantic analysis
- speaker dependent
- image processing