Speaker recognition using Mel frequency Cepstral Coefficients (MFCC) and Vector quantization (VQ) techniques.
Jorge MartínezHéctor Pérez-MeanaEnrique Escamilla HernándezMasahisa Mabo SuzukiPublished in: CONIELECOMP (2012)
Keyphrases
- mel frequency cepstral coefficients
- vector quantization
- speaker recognition
- image compression
- linear predictive
- vector quantizer
- cepstral coefficients
- distortion measure
- speaker identification
- vector quantized
- gaussian mixture model
- speaker diarization
- acoustic features
- principal component analysis
- feature vectors
- codebook design
- index table
- neural network
- finite state vector quantization
- reduced complexity
- fractal image coding
- speech signal
- visual information
- wavelet transform
- pattern recognition
- codebook generation
- multiscale
- computer vision