Feature Compensation with Model-Based Estimation for Noise Masking

Young Joon KIM; Nam Soo KIM

doi:10.1093/ietisy/e90-d.2.603

Feature Compensation with Model-Based Estimation for Noise Masking

Young Joon KIM, Nam Soo KIM

Full Text Views

0

Share
Cite this

Summary :

In this letter, we propose a new approach to estimate the degree of noise masking based on a sophisticated model for clean speech distribution. This measure, named as noise masking probability (NMP), is incorporated into the feature compensation technique to achieve robust speech recognition in noisy environments. Experimental results show that the proposed approach improves the performance of the baseline recognition system in the presence of various background noises.

Publication: IEICE TRANSACTIONS on Information Vol.E90-D No.2 pp.603-605

Publication Date: 2007/02/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e90-d.2.603

Type of Manuscript: LETTER

Category: Speech and Hearing

Cite this

Copy

Young Joon KIM, Nam Soo KIM, "Feature Compensation with Model-Based Estimation for Noise Masking" in IEICE TRANSACTIONS on Information, vol. E90-D, no. 2, pp. 603-605, February 2007, doi: 10.1093/ietisy/e90-d.2.603.
Abstract: In this letter, we propose a new approach to estimate the degree of noise masking based on a sophisticated model for clean speech distribution. This measure, named as noise masking probability (NMP), is incorporated into the feature compensation technique to achieve robust speech recognition in noisy environments. Experimental results show that the proposed approach improves the performance of the baseline recognition system in the presence of various background noises.
URL: https://globals.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.2.603/_p

Copy

@ARTICLE{e90-d_2_603,
author={Young Joon KIM, Nam Soo KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Feature Compensation with Model-Based Estimation for Noise Masking},
year={2007},
volume={E90-D},
number={2},
pages={603-605},
abstract={In this letter, we propose a new approach to estimate the degree of noise masking based on a sophisticated model for clean speech distribution. This measure, named as noise masking probability (NMP), is incorporated into the feature compensation technique to achieve robust speech recognition in noisy environments. Experimental results show that the proposed approach improves the performance of the baseline recognition system in the presence of various background noises.},
keywords={},
doi={10.1093/ietisy/e90-d.2.603},
ISSN={1745-1361},
month={February},}

Copy

TY - JOUR
TI - Feature Compensation with Model-Based Estimation for Noise Masking
T2 - IEICE TRANSACTIONS on Information
SP - 603
EP - 605
AU - Young Joon KIM
AU - Nam Soo KIM
PY - 2007
DO - 10.1093/ietisy/e90-d.2.603
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2007
AB - In this letter, we propose a new approach to estimate the degree of noise masking based on a sophisticated model for clean speech distribution. This measure, named as noise masking probability (NMP), is incorporated into the feature compensation technique to achieve robust speech recognition in noisy environments. Experimental results show that the proposed approach improves the performance of the baseline recognition system in the presence of various background noises.
ER -