Exploiting spatial-temporal feature distribution characteristics for robust speech recognition.
Wei-Hau ChenShih-Hsiang LinBerlin ChenPublished in: INTERSPEECH (2008)
Keyphrases
- speech recognition
- spatial temporal
- noisy environments
- hidden markov models
- automatic speech recognition
- language model
- pattern recognition
- speech recognizer
- spatial and temporal
- cepstral coefficients
- temporal information
- speech signal
- speech recognition technology
- action recognition
- spatio temporal
- speech synthesis
- image features
- speaker identification
- speaker adaptation
- video shots
- speaker independent
- machine learning