Dynamically configurable acoustic models for speech recognition.
Mei-Yuh HwangXuedong HuangPublished in: ICASSP (1998)
Keyphrases
- speech recognition
- acoustic models
- speech recognizer
- speaker independent
- hidden markov models
- automatic speech recognition
- language model
- pattern recognition
- speech signal
- noisy environments
- speech recognition systems
- speaker identification
- machine learning
- neural network
- multi modal
- speaker recognition
- feature space
- feature extraction