DocumentCode :
774761
Title :
Histogram equalization of speech representation for robust speech recognition
Author :
De la Torre, Ángel ; Peinado, Antonio M. ; Segura, José C. ; Pérez-Córdoba, José L. ; Benítez, Ma Carmen ; Rubio, Antonio J.
Author_Institution :
Dept. de Electron. y Tecnologia de Computadores, Univ. de Granada, Spain
Volume :
13
Issue :
3
fYear :
2005
fDate :
5/1/2005 12:00:00 AM
Firstpage :
355
Lastpage :
366
Abstract :
This paper describes a method of compensating for nonlinear distortions in speech representation caused by noise. The method described here is based on the histogram equalization method often used in digital image processing. Histogram equalization is applied to each component of the feature vector in order to improve the robustness of speech recognition systems. The paper describes how the proposed method can be applied to robust speech recognition and it is compared with other compensation techniques. The recognition experiments, including results in the AURORA II framework, demonstrate the effectiveness of histogram equalization when it is applied either alone or in combination with other compensation techniques.
Keywords :
equalisers; nonlinear distortion; speech recognition; digital image processing; feature vector; histogram equalization; nonlinear distortion; speech recognition; speech representation; Acoustic distortion; Acoustic noise; Additive noise; Degradation; Histograms; Noise robustness; Nonlinear distortion; Speech enhancement; Speech recognition; Taylor series; Cepstral mean normalization; Mel frequency cepstral coefficients; histogram equalization; mean and variance normalization; probability density function (pdf); robust speech recognition; vector Taylor series approach;
fLanguage :
English
Journal_Title :
Speech and Audio Processing, IEEE Transactions on
Publisher :
ieee
ISSN :
1063-6676
Type :
jour
DOI :
10.1109/TSA.2005.845805
Filename :
1420370
Link To Document :
بازگشت