Speech Enhancement by Overweighting Gain with Nonlinear Structure in Wavelet Packet Transform

Sung-il JUNG; Younghun KWON; Sung-il YANG

doi:10.1093/ietcom/e90-b.8.2147

Speech Enhancement by Overweighting Gain with Nonlinear Structure in Wavelet Packet Transform

Sung-il JUNG, Younghun KWON, Sung-il YANG

Full Text Views

0

Share
Cite this

Summary :

A speech enhancement method is proposed that can be implemented efficiently due to its use of wavelet packet transform. The proposed method uses a modified spectral subtraction with noise estimation by a least-squares line method and with an overweighting gain per subband with nonlinear structure, where the overweighting gain is used for suppressing the residue of musical noise and the subband is used for applying the weighted values according to the change of signals. The enhanced speech by our method has the following properties: 1) the speech intelligibility can be assured reliably; 2) the musical noise can be reduced efficiently. Various assessments confirmed that the performance of the proposed method was better than that of the compared methods in various noise-level conditions. Especially, the proposed method showed good results even at low SNR.

Publication: IEICE TRANSACTIONS on Communications Vol.E90-B No.8 pp.2147-2150

Publication Date: 2007/08/01

Publicized

Online ISSN: 1745-1345

DOI: 10.1093/ietcom/e90-b.8.2147

Type of Manuscript: LETTER

Category: Fundamental Theories for Communications

Cite this

Copy

Sung-il JUNG, Younghun KWON, Sung-il YANG, "Speech Enhancement by Overweighting Gain with Nonlinear Structure in Wavelet Packet Transform" in IEICE TRANSACTIONS on Communications, vol. E90-B, no. 8, pp. 2147-2150, August 2007, doi: 10.1093/ietcom/e90-b.8.2147.
Abstract: A speech enhancement method is proposed that can be implemented efficiently due to its use of wavelet packet transform. The proposed method uses a modified spectral subtraction with noise estimation by a least-squares line method and with an overweighting gain per subband with nonlinear structure, where the overweighting gain is used for suppressing the residue of musical noise and the subband is used for applying the weighted values according to the change of signals. The enhanced speech by our method has the following properties: 1) the speech intelligibility can be assured reliably; 2) the musical noise can be reduced efficiently. Various assessments confirmed that the performance of the proposed method was better than that of the compared methods in various noise-level conditions. Especially, the proposed method showed good results even at low SNR.
URL: https://globals.ieice.org/en_transactions/communications/10.1093/ietcom/e90-b.8.2147/_p

Copy

@ARTICLE{e90-b_8_2147,
author={Sung-il JUNG, Younghun KWON, Sung-il YANG, },
journal={IEICE TRANSACTIONS on Communications},
title={Speech Enhancement by Overweighting Gain with Nonlinear Structure in Wavelet Packet Transform},
year={2007},
volume={E90-B},
number={8},
pages={2147-2150},
abstract={A speech enhancement method is proposed that can be implemented efficiently due to its use of wavelet packet transform. The proposed method uses a modified spectral subtraction with noise estimation by a least-squares line method and with an overweighting gain per subband with nonlinear structure, where the overweighting gain is used for suppressing the residue of musical noise and the subband is used for applying the weighted values according to the change of signals. The enhanced speech by our method has the following properties: 1) the speech intelligibility can be assured reliably; 2) the musical noise can be reduced efficiently. Various assessments confirmed that the performance of the proposed method was better than that of the compared methods in various noise-level conditions. Especially, the proposed method showed good results even at low SNR.},
keywords={},
doi={10.1093/ietcom/e90-b.8.2147},
ISSN={1745-1345},
month={August},}

Copy

TY - JOUR
TI - Speech Enhancement by Overweighting Gain with Nonlinear Structure in Wavelet Packet Transform
T2 - IEICE TRANSACTIONS on Communications
SP - 2147
EP - 2150
AU - Sung-il JUNG
AU - Younghun KWON
AU - Sung-il YANG
PY - 2007
DO - 10.1093/ietcom/e90-b.8.2147
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E90-B
IS - 8
JA - IEICE TRANSACTIONS on Communications
Y1 - August 2007
AB - A speech enhancement method is proposed that can be implemented efficiently due to its use of wavelet packet transform. The proposed method uses a modified spectral subtraction with noise estimation by a least-squares line method and with an overweighting gain per subband with nonlinear structure, where the overweighting gain is used for suppressing the residue of musical noise and the subband is used for applying the weighted values according to the change of signals. The enhanced speech by our method has the following properties: 1) the speech intelligibility can be assured reliably; 2) the musical noise can be reduced efficiently. Various assessments confirmed that the performance of the proposed method was better than that of the compared methods in various noise-level conditions. Especially, the proposed method showed good results even at low SNR.
ER -