• Volume/Page
  • Keyword
  • DOI
  • Citation
  • Advanced
   
 
 
 

Journal of the Acoustical Society of America

BROWSE VOLUMES

Year Range: 
Search Issue | RSS Feeds RSS
Previous Issue Next Issue

May 2012

Volume 131, Issue 5, pp. EL355-4232

Return to All Sections
back to top
RSS Feeds

Spectro-temporal modulation subspace-spanning filter bank features for robust automatic speech recognition

Marc René Schädler, Bernd T. Meyer, and Birger Kollmeier

J. Acoust. Soc. Am. Volume 131, Issue 5, pp. 4134-4151 (2012); (18 pages)

Full Text: Read Online (HTML) | Download PDF

Show Abstract
In an attempt to increase the robustness of automatic speech recognition (ASR) systems, a feature extraction scheme is proposed that takes spectro-temporal modulation frequencies (MF) into account. This physiologically inspired approach uses a two-dimensional filter bank based on Gabor filters, which limits the redundant information between feature components, and also results in physically interpretable features. Robustness against extrinsic variation (different types of additive noise) and intrinsic variability (arising from changes in speaking rate, effort, and style) is quantified in a series of recognition experiments. The results are compared to reference ASR systems using Mel-frequency cepstral coefficients (MFCCs), MFCCs with cepstral mean subtraction (CMS) and RASTA-PLP features, respectively. Gabor features are shown to be more robust against extrinsic variation than the baseline systems without CMS, with relative improvements of 28% and 16% for two training conditions (using only clean training samples or a mixture of noisy and clean utterances, respectively). When used in a state-of-the-art system, improvements of 14% are observed when spectro-temporal features are concatenated with MFCCs, indicating the complementarity of those feature types. An analysis of the importance of specific MF shows that temporal MF up to 25 Hz and spectral MF up to 0.25 cycles/channel are beneficial for ASR.
Show PACS
43.72.Ne Automatic speech recognition systems
43.60.Lq Acoustic imaging, displays, pattern recognition, feature extraction
43.60.Hj Time-frequency signal processing, wavelets
43.72.Ar Speech analysis and analysis techniques; parametric representation of speech
Return to All Sections
Close

Home Publications Meetings Contact ASA Site Map Back to Top

Copyright © Acoustical Society of America

close