Robust Feature Extraction Using Variable Window Function in Autocorrelation Domain for Speech Recognition
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.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E92-A No.11 pp.2917-2921
- Publication Date
- 2009/11/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E92.A.2917
- Type of Manuscript
- LETTER
- Category
- Speech and Hearing
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Sangho LEE, Jeonghyun HA, Jaekeun HONG, "Robust Feature Extraction Using Variable Window Function in Autocorrelation Domain for Speech Recognition" in IEICE TRANSACTIONS on Fundamentals,
vol. E92-A, no. 11, pp. 2917-2921, November 2009, doi: 10.1587/transfun.E92.A.2917.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E92.A.2917/_p
Copy
@ARTICLE{e92-a_11_2917,
author={Sangho LEE, Jeonghyun HA, Jaekeun HONG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Robust Feature Extraction Using Variable Window Function in Autocorrelation Domain for Speech Recognition},
year={2009},
volume={E92-A},
number={11},
pages={2917-2921},
abstract={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.},
keywords={},
doi={10.1587/transfun.E92.A.2917},
ISSN={1745-1337},
month={November},}
Copy
TY - JOUR
TI - Robust Feature Extraction Using Variable Window Function in Autocorrelation Domain for Speech Recognition
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2917
EP - 2921
AU - Sangho LEE
AU - Jeonghyun HA
AU - Jaekeun HONG
PY - 2009
DO - 10.1587/transfun.E92.A.2917
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E92-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 2009
AB - 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.
ER -
English
