Combined wideband speech enhancement method based on statistical model and EMD

A combined wideband speech enhancement method based on statistical model and empirical mode decomposition (EMD) was proposed.First,statistical model was used to eliminate the main noise component in noisy speech.Then,the residual noise was further suppressed by a post-processing module which is a sp...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuan ZHOU, Chang-chun BAO, Bing-yin XIA
Format: Article
Language:zho
Published: Editorial Department of Journal on Communications 2013-08-01
Series:Tongxin xuebao
Subjects:
Online Access:http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2013.08.013/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841539855976235008
author Xuan ZHOU
Chang-chun BAO
Bing-yin XIA
author_facet Xuan ZHOU
Chang-chun BAO
Bing-yin XIA
author_sort Xuan ZHOU
collection DOAJ
description A combined wideband speech enhancement method based on statistical model and empirical mode decomposition (EMD) was proposed.First,statistical model was used to eliminate the main noise component in noisy speech.Then,the residual noise was further suppressed by a post-processing module which is a speech enhancement algorithm with voice activity detection (VAD) based on EMD.The advantages of the two methods were combined effectively.The performance of the proposed method was evaluated under the standard of ITU-T G160.The experimental results indicate that the algorithm is more effective for improving the SNR in the different noise environments than classical statistical model approach.Meanwhile,in low SNR conditions,musical noise is reduced effectively,and the speech sounds more comfortable.
format Article
id doaj-art-fc8edd3159ac4e5a9a10e8adc00cdf9b
institution Kabale University
issn 1000-436X
language zho
publishDate 2013-08-01
publisher Editorial Department of Journal on Communications
record_format Article
series Tongxin xuebao
spelling doaj-art-fc8edd3159ac4e5a9a10e8adc00cdf9b2025-01-14T06:41:04ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2013-08-01349510159674250Combined wideband speech enhancement method based on statistical model and EMDXuan ZHOUChang-chun BAOBing-yin XIAA combined wideband speech enhancement method based on statistical model and empirical mode decomposition (EMD) was proposed.First,statistical model was used to eliminate the main noise component in noisy speech.Then,the residual noise was further suppressed by a post-processing module which is a speech enhancement algorithm with voice activity detection (VAD) based on EMD.The advantages of the two methods were combined effectively.The performance of the proposed method was evaluated under the standard of ITU-T G160.The experimental results indicate that the algorithm is more effective for improving the SNR in the different noise environments than classical statistical model approach.Meanwhile,in low SNR conditions,musical noise is reduced effectively,and the speech sounds more comfortable.http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2013.08.013/wideband speech enhancementstatistical modelEMDVAD
spellingShingle Xuan ZHOU
Chang-chun BAO
Bing-yin XIA
Combined wideband speech enhancement method based on statistical model and EMD
Tongxin xuebao
wideband speech enhancement
statistical model
EMD
VAD
title Combined wideband speech enhancement method based on statistical model and EMD
title_full Combined wideband speech enhancement method based on statistical model and EMD
title_fullStr Combined wideband speech enhancement method based on statistical model and EMD
title_full_unstemmed Combined wideband speech enhancement method based on statistical model and EMD
title_short Combined wideband speech enhancement method based on statistical model and EMD
title_sort combined wideband speech enhancement method based on statistical model and emd
topic wideband speech enhancement
statistical model
EMD
VAD
url http://www.joconline.com.cn/zh/article/doi/10.3969/j.issn.1000-436x.2013.08.013/
work_keys_str_mv AT xuanzhou combinedwidebandspeechenhancementmethodbasedonstatisticalmodelandemd
AT changchunbao combinedwidebandspeechenhancementmethodbasedonstatisticalmodelandemd
AT bingyinxia combinedwidebandspeechenhancementmethodbasedonstatisticalmodelandemd