Accelerate training by DWT in speaker identification using SVMs.
Zhenchun LeiZhaohui WuYingchun YangPublished in: SMC (1) (2004)
Keyphrases
- speaker identification
- training set
- support vector
- speech recognition
- discrete wavelet transform
- speech signal
- gaussian mixture model
- multiresolution
- multi class
- feature extraction
- noisy environments
- wavelet transform
- kernel function
- hidden markov models
- hyperplane
- broadcast news
- knn
- machine learning
- feature space
- pattern recognition
- training data
- image processing
- feature selection
- computer vision