Auditory model based speech feature extraction and its application to speaker identification.
Bing XiangXihong WuZhimin LiuHuisheng ChiPublished in: IJCNN (1999)
Keyphrases
- speaker identification
- feature extraction
- speech processing
- speech signal
- visual speech
- speech recognition
- speaker recognition
- gaussian mixture model
- speaker dependent
- mel frequency cepstral coefficients
- feature transformation
- noisy environments
- broadcast news
- signal processing
- speaker independent
- image classification
- image processing
- pattern recognition
- visual information
- feature set
- feature vectors
- face recognition
- feature selection
- high level
- non stationary
- sound source
- mixture model
- em algorithm