Using Gaussian mixture modeling in speech recognition.
Yaxin ZhangMichael D. AlderRoberto TogneriPublished in: ICASSP (1) (1994)
Keyphrases
- speech recognition
- gaussian mixture modeling
- gaussian mixture model
- image representation
- hidden markov models
- speech processing
- automatic speech recognition
- pattern recognition
- rate control scheme
- language model
- speech recognizer
- speech signal
- speaker identification
- speech synthesis
- speech recognition systems
- speech recognition technology
- noisy environments
- rate control
- speaker dependent
- speaker independent
- machine learning
- multiscale
- feature extraction