Frequency and Wavelet Filtering for Robust Speech Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2003

Frequency and Wavelet Filtering for Robust Speech Recognition

Abstract

Mel-frequency cepstral coefficients (MFCC) are the most widely used features in current speech recognition systems. However, they have a poor physical interpretation and they do not lie in the frequency domain. Frequency filtering (FF) is a technique that has been recently developed to design frequency-localized speech features that perform similar to MFCC in terms of recognition performances. Motivated by our desire to build time-frequency speech models, we wanted to use the FF technique as front-end. However, when evaluating FF on the Aurora-3 database we found some discrepancies in the highly mismatch case. This led us to put FF in another perspective: the wavelet transform. By doing so, we were able to explain the discrepancies and to achieve significant improvements in recognition in the highly mismatch case.
No file

Dates and versions

inria-00099753 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00099753 , version 1

Cite

Murat Deviren, Khalid Daoudi. Frequency and Wavelet Filtering for Robust Speech Recognition. Artificial Neural Networks and Neural Information Processing - Joint International Conference ICANN/ICONIP2003, 2003, Istanbul, Turquie, pp.452-462. ⟨inria-00099753⟩
56 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More