Choice of Mel filter bank in computing MFCC of a resampled speech.
Sunil Kumar KopparapuLaxmi Narayana M.Published in: ISSPA (2010)
Keyphrases
- filter bank
- speech recognition
- cepstral coefficients
- image coding
- speech signal
- subband
- linear prediction
- multiresolution
- multiscale
- perfect reconstruction
- wavelet packet
- signal processing
- discrete cosine transform
- computationally efficient
- frequency domain
- speaker recognition
- wavelet filters
- spectral analysis
- feature extraction
- low pass
- speaker identification
- reconstruction error
- feature vectors
- subband coding
- optimal filter
- high frequency
- automatic speech recognition
- feature set
- machine learning
- wavelet decomposition
- neural network
- gaussian mixture model
- audio signal
- wavelet coefficients
- acoustic features
- finite impulse response
- speaker diarization
- bit rate
- language model
- hidden markov models