Speech Enhancement Algorithm Using Recursive Wavelet Shrinkage

Gihyoun LEE; Sung Dae NA; KiWoong SEONG; Jin-Ho CHO; Myoung Nam KIM

doi:10.1587/transinf.2015EDL8251

Speech Enhancement Algorithm Using Recursive Wavelet Shrinkage

Gihyoun LEE, Sung Dae NA, KiWoong SEONG, Jin-Ho CHO, Myoung Nam KIM

Full Text Views

0

Cite this

Summary :

Because wavelet transforms have the characteristic of decomposing signals that are similar to the human acoustic system, speech enhancement algorithms that are based on wavelet shrinkage are widely used. In this paper, we propose a new speech enhancement algorithm of hearing aids based on wavelet shrinkage. The algorithm has multi-band threshold value and a new wavelet shrinkage function for recursive noise reduction. We performed experiments using various types of authorized speech and noise signals, and our results show that the proposed algorithm achieves significantly better performances compared with other recently proposed speech enhancement algorithms using wavelet shrinkage.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.7 pp.1945-1948

Publication Date: 2016/07/01

Publicized: 2016/03/30

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDL8251

Type of Manuscript: LETTER

Category: Speech and Hearing

Authors

Gihyoun LEE
  Kyungpook National University
Sung Dae NA
  Kyungpook National University
KiWoong SEONG
  Kyungpook National University Hospital
Jin-Ho CHO
  Kyungpook National University
Myoung Nam KIM
  Kyungpook National University

Keyword

speech enhancement, wavelet shrinkage, recursive algorithm, hearing aids

Cite this

Copy

Gihyoun LEE, Sung Dae NA, KiWoong SEONG, Jin-Ho CHO, Myoung Nam KIM, "Speech Enhancement Algorithm Using Recursive Wavelet Shrinkage" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 7, pp. 1945-1948, July 2016, doi: 10.1587/transinf.2015EDL8251.
Abstract: Because wavelet transforms have the characteristic of decomposing signals that are similar to the human acoustic system, speech enhancement algorithms that are based on wavelet shrinkage are widely used. In this paper, we propose a new speech enhancement algorithm of hearing aids based on wavelet shrinkage. The algorithm has multi-band threshold value and a new wavelet shrinkage function for recursive noise reduction. We performed experiments using various types of authorized speech and noise signals, and our results show that the proposed algorithm achieves significantly better performances compared with other recently proposed speech enhancement algorithms using wavelet shrinkage.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8251/_p

Copy

@ARTICLE{e99-d_7_1945,
author={Gihyoun LEE, Sung Dae NA, KiWoong SEONG, Jin-Ho CHO, Myoung Nam KIM, },
journal={IEICE TRANSACTIONS on Information},
title={Speech Enhancement Algorithm Using Recursive Wavelet Shrinkage},
year={2016},
volume={E99-D},
number={7},
pages={1945-1948},
abstract={Because wavelet transforms have the characteristic of decomposing signals that are similar to the human acoustic system, speech enhancement algorithms that are based on wavelet shrinkage are widely used. In this paper, we propose a new speech enhancement algorithm of hearing aids based on wavelet shrinkage. The algorithm has multi-band threshold value and a new wavelet shrinkage function for recursive noise reduction. We performed experiments using various types of authorized speech and noise signals, and our results show that the proposed algorithm achieves significantly better performances compared with other recently proposed speech enhancement algorithms using wavelet shrinkage.},
keywords={},
doi={10.1587/transinf.2015EDL8251},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Speech Enhancement Algorithm Using Recursive Wavelet Shrinkage
T2 - IEICE TRANSACTIONS on Information
SP - 1945
EP - 1948
AU - Gihyoun LEE
AU - Sung Dae NA
AU - KiWoong SEONG
AU - Jin-Ho CHO
AU - Myoung Nam KIM
PY - 2016
DO - 10.1587/transinf.2015EDL8251
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2016
AB - Because wavelet transforms have the characteristic of decomposing signals that are similar to the human acoustic system, speech enhancement algorithms that are based on wavelet shrinkage are widely used. In this paper, we propose a new speech enhancement algorithm of hearing aids based on wavelet shrinkage. The algorithm has multi-band threshold value and a new wavelet shrinkage function for recursive noise reduction. We performed experiments using various types of authorized speech and noise signals, and our results show that the proposed algorithm achieves significantly better performances compared with other recently proposed speech enhancement algorithms using wavelet shrinkage.
ER -