A hybrid SVM/DDBHMM decision fusion modeling for robust continuous digital speech recognition.
Jingwei LiuZuoying WangXi XiaoPublished in: Pattern Recognit. Lett. (2007)
Keyphrases
- speech recognition
- decision fusion
- noisy environments
- hidden markov models
- speech synthesis
- digital video library
- speech processing
- speech signal
- language model
- speech recognizer
- automatic speech recognition
- speech recognition technology
- speech recognition systems
- support vector
- pattern recognition
- speaker identification
- feature selection
- digit recognition
- speaker independent
- speech recognizers
- training set
- support vector machine
- isolated word
- machine learning
- fusion process
- maximum likelihood
- high frequency