Discriminatively learned filter bank for acoustic features.
Takumi KobayashiJiaxing YePublished in: ICASSP (2016)
Keyphrases
- filter bank
- acoustic features
- image coding
- subband
- multiscale
- multiresolution
- signal processing
- speaker verification
- frequency domain
- perfect reconstruction
- music information retrieval
- computationally efficient
- visual features
- automatic speech recognition
- wavelet transform
- wavelet filters
- spectral analysis
- speech signal
- cross correlation
- neural network
- discrete wavelet transform
- hidden markov models
- object recognition
- audio features
- speech recognition
- building blocks
- image compression