Modeling acoustic-phonetic detail in an HMM-based large vocabulary speech recognizer.
Li DengMatthew LennigVishwa GuptaPaul MermelsteinPublished in: ICASSP (1988)
Keyphrases
- speech recognizer
- speech recognition
- speaker independent
- speech recognizers
- speech recognition systems
- hidden markov models
- acoustic models
- spoken language
- speech understanding
- broadcast news
- speaker dependent
- speech signal
- language model
- speaker adaptation
- pattern recognition
- speaker identification
- automatic speech recognition
- noisy environments
- machine learning
- query expansion
- natural language
- multimedia
- image processing