Loading...

A model distance maximizing framework for speech recognizer-based speech enhancement

Babaali, B ; Sharif University of Technology | 2011

430 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.aeue.2010.02.002
  3. Publisher: 2011
  4. Abstract:
  5. This paper has presented a novel discriminative parameter calibration approach based on the model distance maximizing (MDM) framework to improve the performance of our previously-proposed method based on spectral subtraction (SS) in a likelihood-maximizing framework. In the previous work, spectral over-subtraction factors were adjusted based on the conventional maximum-likelihood (ML) approach that utilized only the true model and did not consider other confused models, thus likely reached suboptimal solutions. While in the proposed MDM framework, improved speech recognition performance is obtained by maximizing the dissimilarities among models. Experimental results based on FARSDAT, TIMIT and real distant-talking databases have demonstrated that the MDM framework outperformed ML in terms of recognition accuracy. © 2010 Elsevier GmbH. All rights reserved
  6. Keywords:
  7. Model distance maximizing ; Robust speech recognition ; Spectral subtraction ; Speech recognizer-based speech enhancement ; FARSDAT ; Parameter calibration ; Recognition accuracy ; Spectral subtractions ; Speech recognition performance ; Speech recognizer ; Suboptimal solution ; Maximum likelihood ; Optimization ; Speech enhancement ; Speech recognition
  8. Source: AEU - International Journal of Electronics and Communications ; Volume 65, Issue 2 , February , 2011 , Pages 99-106 ; 14348411 (ISSN)
  9. URL: http://www.sciencedirect.com/science/article/pii/S1434841110000336