Wavelet Feature Selection Using Fuzzy Approach to Text Independent Speaker Recognition

  title={Wavelet Feature Selection Using Fuzzy Approach to Text Independent Speaker Recognition},
  author={Shung-Yung Lung},
  journal={IEICE Trans. Fundam. Electron. Commun. Comput. Sci.},
  • Shung-Yung Lung
  • Published 1 March 2005
  • Computer Science
  • IEICE Trans. Fundam. Electron. Commun. Comput. Sci.
A wavelet feature selection derived by using fuzzy evaluation index for speaker identification is described. The concept of a flexible membership function incorporating weighed distance is introduced in the evaluation index to make the modeling of clusters more appropriate. Our results have shown that this feature selection introduced better performance than the wavelet features with respect to the percentages of recognition. 
5 Citations

Figures and Tables from this paper

Hybrid wavelet based LPC features for Hindi speech recognition
Wavelet-Based Linear Prediction Coefficients (WBLPC) are obtained by applying 3 and 4-level wavelet decomposition and then having linear prediction of each sub-bands to get total 13 features.


Feature extracted from wavelet eigenfunction estimation for text-independent speaker recognition
Speech feature extracted from adaptive wavelet for speech recognition
A new speech feature extracted from adaptive wavelet for speech recognition is described, which shows a slightly better recognition rate than the cepstrum for speaker independent speech recognition and shows a lower standard deviation between speakers than does the cEPstrum.
Mel filter-like admissible wavelet packet structure for speech recognition
Wavelet packet transform's multiresolution capabilities are used to derive new sets of features, which are found to be superior to Mel frequency cepstral coefficients (MFCC) in unvoiced phoneme classification problems.
Feature extraction using discrete wavelet transform for speech recognition
  • Z. Tufekci, J. Gowdy
  • Computer Science
    Proceedings of the IEEE SoutheastCon 2000. 'Preparing for The New Millennium' (Cat. No.00CH37105)
  • 2000
Experimental results on a phoneme recognition task showed that a MFDWC-based recognizer gave better results than recognizers based on MFCC, SUB features, and MULT features for white Gaussian noise, band-limited white Gaussia noise and clean speech cases.
Robust text-independent speaker identification using Gaussian mixture speaker models
The individual Gaussian components of a GMM are shown to represent some general speaker-dependent spectral shapes that are effective for modeling speaker identity and is shown to outperform the other speaker modeling techniques on an identical 16 speaker telephone speech task.