Robust Feature Extraction Using Variable Window Function in Autocorrelation Domain for Speech Recognition

Sangho LEE  Jeonghyun HA  Jaekeun HONG  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E92-A   No.11   pp.2917-2921
Publication Date: 2009/11/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E92.A.2917
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Speech and Hearing
Keyword: 
variable window,  AMFCC,  speech recognition,  robust feature,  

Full Text: PDF(584.9KB)
>>Buy this Article


Summary: 
This paper presents a new feature extraction method for robust speech recognition based on the autocorrelation mel frequency cepstral coefficients (AMFCCs) and a variable window. While the AMFCC feature extraction method uses the fixed double-dynamic-range (DDR) Hamming window for higher-lag autocorrelation coefficients, which are least affected by noise, the proposed method applies a variable window, depending on the frame energy and periodicity. The performance of the proposed method is verified using an Aurora-2 task, and the results confirm a significantly improved performance under noisy conditions.