Combining Speech Enhancement and Discriminative Feature Extraction for Robust Speaker Recognition.
Yan ZhangZhenmin TangYanping LiPublished in: CSIE (5) (2009)
Keyphrases
- speaker recognition
- feature extraction
- noisy environments
- speaker identification
- speech enhancement
- speaker verification
- speech signal
- gaussian mixture model
- vector quantization
- speech recognition
- mel frequency cepstral coefficients
- feature space
- image processing
- pattern classification
- feature vectors
- feature selection
- image classification
- signal to noise ratio
- linear prediction
- frequency domain
- computer vision
- noise reduction
- principal component analysis
- hidden markov models