XJIPC OpenIR  > 多语种信息技术研究室
DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction
Bai, HC (Bai, Haichuan)[ 1,2 ]; Ge, FP (Ge, Fengpei)[ 1,2 ]; Yan, YH (Yan, Yonghong)[ 1,2,3 ]
2018
发表期刊CHINA COMMUNICATIONS
ISSN1673-5447
卷号15期号:9页码:235-243
摘要

This paper presents a deep neural network (DNN)-based speech enhancement algorithm based on the soft audible noise masking for the single-channel wind noise reduction. To reduce the low-frequency residual noise, the psychoacoustic model is adopted to calculate the masking threshold from the estimated clean speech spectrum. The gain for noise suppression is obtained based on soft audible noise masking by comparing the estimated wind noise spectrum with the masking threshold. To deal with the abruptly time-varying noisy signals, two separate DNN models are utilized to estimate the spectra of clean speech and wind noise components. Experimental results on the subjective and objective quality tests show that the proposed algorithm achieves the better performance compared with the conventional DNN-based wind noise reduction method.

关键词Wind Noise Reduction Speech Enhancement Soft Audible Noise Masking Psychoacoustic Model Deep Neural Network
DOI10.1109/CC.2018.8456465
收录类别SCI
WOS记录号WOS:000443309800019
引用统计
文献类型期刊论文
条目标识符http://ir.xjipc.cas.cn/handle/365002/5555
专题多语种信息技术研究室
作者单位1.Chinese Acad Sci, Inst Acoust, Key Lab Speech Acoust & Content Understanding, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Xinjiang Tech Inst Phys & Chem, Xinjiang Lab Minor Speech & Language Informat Pro, Urumqi 830011, Peoples R China
推荐引用方式
GB/T 7714
Bai, HC ,Ge, FP ,Yan, YH . DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction[J]. CHINA COMMUNICATIONS,2018,15(9):235-243.
APA Bai, HC ,Ge, FP ,&Yan, YH .(2018).DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction.CHINA COMMUNICATIONS,15(9),235-243.
MLA Bai, HC ,et al."DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction".CHINA COMMUNICATIONS 15.9(2018):235-243.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
DNN-Based Speech Enh(1080KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Bai, HC (Bai, Haichuan)[ 1,2 ]]的文章
[Ge, FP (Ge, Fengpei)[ 1,2 ]]的文章
[Yan, YH (Yan, Yonghong)[ 1,2,3 ]]的文章
百度学术
百度学术中相似的文章
[Bai, HC (Bai, Haichuan)[ 1,2 ]]的文章
[Ge, FP (Ge, Fengpei)[ 1,2 ]]的文章
[Yan, YH (Yan, Yonghong)[ 1,2,3 ]]的文章
必应学术
必应学术中相似的文章
[Bai, HC (Bai, Haichuan)[ 1,2 ]]的文章
[Ge, FP (Ge, Fengpei)[ 1,2 ]]的文章
[Yan, YH (Yan, Yonghong)[ 1,2,3 ]]的文章
相关权益政策
暂无数据
收藏/分享
文件名: DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。