Discriminative of wavelet sub-signals for speech recognition.
Chao-Yin HsiaoChin-Kun TengPaohwa YangHao Ming HuangPublished in: ICCA (2014)
Keyphrases
- speech recognition
- noisy environments
- language model
- hidden markov models
- automatic speech recognition
- feature extraction
- speech signal
- speech recognizer
- speech synthesis
- speech recognition technology
- wavelet transform
- speech processing
- pattern recognition
- signal processing
- speech recognition systems
- power spectrum
- wavelet coefficients
- spectral analysis
- denoising
- multiscale
- discriminative training
- cepstral coefficients
- speech recognition errors
- feature selection
- isolated word
- speaker identification
- multiresolution
- speaker independent
- independent component analysis
- wavelet decomposition
- neural network