Subband acoustic waveform front-end for robust speech recognition using support vector machines.
Jibran YousafzaiZoran CvetkovicPeter SollichPublished in: SLT (2010)
Keyphrases
- speech recognition
- subband
- speech recognition systems
- frequency domain
- filter bank
- speaker independent
- noisy environments
- image compression
- speech recognizers
- wavelet transform
- bit rate
- multiresolution
- hidden markov models
- high frequency
- feature vectors
- speech synthesis
- language model
- wavelet coefficients
- wavelet decomposition
- wavelet domain
- speech signal
- acoustic models
- speech recognizer
- automatic speech recognition
- frequency band
- pattern recognition
- noisy speech
- image coder
- speaker identification
- low frequency
- discrete wavelet transform
- wavelet packet
- linear prediction
- image coding
- video coding
- neural network
- cross correlation