Discriminative Enhancement for Single Channel Audio Source Separation Using Deep Neural Networks

被引：5

作者：

Grais, Emad M. ^{[1
]}

Roma, Gerard ^{[1
]}

Simpson, Andrew J. R. ^{[1
]}

Plumbley, Mark D. ^{[1
]}

机构：

[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford, Surrey, England

来源：

LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2017) | 2017年 / 10169卷

基金：

英国工程与自然科学研究理事会;

关键词：

Single channel audio source separation; Deep neural networks; Audio enhancement; Discriminative training;

D O I：

10.1007/978-3-319-53547-0_23

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

The sources separated by most single channel audio source separation techniques are usually distorted and each separated source contains residual signals from the other sources. To tackle this problem, we propose to enhance the separated sources to decrease the distortion and interference between the separated sources using deep neural networks (DNNs). Two different DNNs are used in this work. The first DNN is used to separate the sources from the mixed signal. The second DNN is used to enhance the separated signals. To consider the interactions between the separated sources, we propose to use a single DNN to enhance all the separated sources together. To reduce the residual signals of one source from the other separated sources (interference), we train the DNN for enhancement discriminatively to maximize the dissimilarity between the predicted sources. The experimental results show that using discriminative enhancement decreases the distortion and interference between the separated sources.

引用

页码：236 / 246

页数：11

共 50 条

[1] Combining Mask Estimates for Single Channel Audio Source Separation using Deep Neural Networks
Grais, Emad M.
Roma, Gerard
Simpson, Andrew J. R.
Plumbley, Mark D.
[J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3339 - 3343
[2] Two-Stage Single-Channel Audio Source Separation Using Deep Neural Networks
Grais, Emad M.
Roma, Gerard
Simpson, Andrew J. R.
Plumbley, Mark D.
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2017, 25 (09) : 1469 - 1479
[3] On Discriminative Framework for Single Channel Audio Source Separation
Gang, Arpita
Biyani, Pravesh
[J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 565 - 569
[4] DEEP NEURAL NETWORKS FOR SINGLE CHANNEL SOURCE SEPARATION
Grais, Emad M.
Sen, Mehmet Umut
Erdogan, Hakan
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[5] Single Channel Speech Source Separation Using Hierarchical Deep Neural Networks
Noorani, Seyed Majid
Seyedin, Sanaz
[J]. 2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 466 - 470
[6] Monoaural Audio Source Separation Using Deep Convolutional Neural Networks
Chandna, Pritish
Miron, Marius
Janer, Jordi
Gomez, Emilia
[J]. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2017), 2017, 10169 : 258 - 266
[7] Ensemble System of Deep Neural Networks for Single-Channel Audio Separation
Al-Kaltakchi, Musab T. S.
Mohammad, Ahmad Saeed
Woo, Wai Lok
[J]. INFORMATION, 2023, 14 (07)
[8] Multichannel Audio Source Separation With Deep Neural Networks
Nugraha, Aditya Arie
Liutkus, Antoine
Vincent, Emmanuel
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2016, 24 (09) : 1652 - 1664
[9] Audio Source Separation with Discriminative Scattering Networks
Sprechmann, Pablo
Bruna, Joan
LeCun, Yann
[J]. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION, LVA/ICA 2015, 2015, 9237 : 259 - 267
[10] Referenceless Performance Evaluation of Audio Source Separation using Deep Neural Networks
Grais, Emad M.
Wierstorf, Hagen
Ward, Dominic
Mason, Russell
Plumbley, Mark D.
[J]. 2019 27TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2019,

← 1 2 3 4 5 →