Acoustic features for speech recognition based on Gammatone filterbank and instantaneous frequency.
Hui YinVolker HohmannCliment NadeuPublished in: Speech Commun. (2011)
Keyphrases
- speech recognition
- acoustic features
- filter bank
- instantaneous frequency
- speech signal
- automatic speech recognition
- spectral analysis
- subband
- hidden markov models
- multiscale
- multiresolution
- noisy environments
- language model
- pattern recognition
- non stationary
- speaker identification
- speaker verification
- signal processing
- frequency domain
- mel frequency cepstral coefficients
- music information retrieval
- speaker recognition
- image compression
- spectral features
- computer vision
- cepstral coefficients
- image segmentation
- computational complexity
- multi modal
- visual features