DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction

被引：0
|
作者：
Haichuan Bai [1 ,2 ]
Fengpei Ge [1 ,2 ]
Yonghong Yan [1 ,2 ,3 ]
机构：
[1] Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences
[2] University of Chinese Academy of Sciences
[3] Xinjiang Laboratory of Minority Speech and Language Information Processing, Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences
来源：
China Communications | 2018年 / 15卷 / 09期
基金：
中国国家自然科学基金;
关键词：
wind noise reduction; speech enhancement; soft audible noise masking; psychoacoustic model; deep neural network;
D O I：
暂无
中图分类号：
TN912.35 [语音增强];
学科分类号：
0711 ;
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.
引用
收藏
页码：235 / 243
页数：9
相关论文
共 50 条
  • [1] DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction
    Bai, Haichuan
    Ge, Fengpei
    Yan, Yonghong
    [J]. CHINA COMMUNICATIONS, 2018, 15 (09) : 235 - 243
  • [2] Speech enhancement based on soft audible noise masking and noise power estimation
    Yu, Rongshan
    [J]. SPEECH COMMUNICATION, 2013, 55 (10) : 964 - 974
  • [3] An Adaptation Method in Noise Mismatch Conditions for DNN-based Speech Enhancement
    Xu Si-Ying
    Niu Tong
    Qu Dan
    Long Xing-Yan
    [J]. KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2018, 12 (10): : 4930 - 4951
  • [4] Audible noise reduction in eigendomain for speech enhancement
    You, Chang Huai
    Rahardja, Susanto
    Koh, Soo Ngee
    [J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (06): : 1753 - 1765
  • [5] Signal subspace speech enhancement for audible noise reduction
    You, CH
    Koh, SN
    Rahardja, S
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 145 - 148
  • [6] Speech enhancement based on audible noise suppression
    Tsoukalas, DE
    Mourjopoulos, JN
    Kokkinakis, G
    [J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1997, 5 (06): : 497 - 514
  • [7] Concatenated Identical DNN (CI-DNN) to Reduce Noise-Type Dependence in DNN-Based Speech Enhancement
    Xu, Ziyi
    Strake, Maximilian
    Fingscheidt, Tim
    [J]. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,
  • [8] DNN-BASED SPEECH ENHANCEMENT USING MBE MODEL
    Huang, Qizheng
    Bao, Changchun
    Wang, Xianyun
    Xiang, Yang
    [J]. 2018 16TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), 2018, : 196 - 200
  • [9] ILMSAF based speech enhancement with DNN and noise classification
    Li, Ruwei
    Liu, Yanan
    Shi, Yongqiang
    Dong, Liang
    Cui, Weili
    [J]. SPEECH COMMUNICATION, 2016, 85 : 53 - 70
  • [10] ON GENERATING MIXING NOISE SIGNALS WITH BASIS FUNCTIONS FOR SIMULATING NOISY SPEECH AND LEARNING DNN-BASED SPEECH ENHANCEMENT MODELS
    Wen, Shi-Xue
    Du, Jun
    Lee, Chin-Hui
    [J]. 2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2017,
12345