Histogram Equalization Utilizing Window-Based Smoothed CDF Estimation for Feature Compensation

Youngjoo SUH
Hoirin KIM
Munchurl KIM

IEICE TRANSACTIONS on Information and Systems   Vol.E91-D    No.8    pp.2199-2202
Publication Date: 2008/08/01
Online ISSN: 1745-1361
DOI: 10.1093/ietisy/e91-d.8.2199
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Speech and Hearing
feature compensation,  histogram equalization,  robust speech recognition,  window-based CDF estimation,  

Full Text: PDF(176.5KB)>>
Buy this Article

In this letter, we propose a new histogram equalization method to compensate for acoustic mismatches mainly caused by corruption of additive noise and channel distortion in speech recognition. The proposed method employs an improved test cumulative distribution function (CDF) by more accurately smoothing the conventional order statistics-based test CDF with the use of window functions for robust feature compensation. Experiments on the AURORA 2 framework confirmed that the proposed method is effective in compensating speech recognition features by reducing the averaged relative error by 13.12% over the order statistics-based conventional histogram equalization method and by 58.02% over the mel-cepstral-based features for the three test sets.

open access publishing via