Multichannel Singing Voice Separation by Deep Neural Network Informed DOA Constrained CMNMF

被引:0
|
作者
Munoz-Montoro, Antonio J. [1 ]
Politis, Archontis [2 ]
Drossos, Konstantinos [2 ]
Carabias-Orti, Julio J. [1 ]
机构
[1] Univ Jaen, Telecommun Engn Dept, Jaen, Spain
[2] Tampere Univ, Audio Res Grp, Tampere, Finland
基金
欧洲研究理事会;
关键词
Multichannel Source Separation; Singing Voice; Deep Learning; CMNMF; Spatial Audio; SPATIAL COVARIANCE MODEL; AUDIO SOURCE SEPARATION; NONNEGATIVE MATRIX;
D O I
暂无
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This work addresses the problem of multichannel source separation combining two powerful approaches, multichannel spectral factorization with recent monophonic deep learning (DL) based spectrum inference. Individual source spectra at different channels are estimated with a Masker-Denoiser twin network, able to model long-term temporal patterns of a musical piece. The monophonic source spectrograms are used within a spatial covariance mixing model based on complex-valued multichannel non-negative matrix factorization (CMNMF) that predicts the spatial characteristics of each source. The proposed framework is evaluated on the task of singing voice separation with a large multichannel dataset. Experimental results show that our joint DL+CMNMF method outperforms both the individual monophonic DL-based separation and the multichannel CMNMF baseline methods.
引用
收藏
页数:6
相关论文
共 50 条
  • [41] Deep Convolutional Neural Network for Voice Liveness Detection
    Gupta, Siddhant
    Khoria, Kuldeep
    Patil, Ankur T.
    Patil, Hemant A.
    2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 775 - 779
  • [42] Comparative study of singing voice detection based on deep neural networks and ensemble learning
    You, Shingchern D.
    Liu, Chien-Hung
    Chen, Woei-Kae
    HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES, 2018, 8
  • [43] Fractional deep neural network via constrained optimization
    Antil, Harbir
    Khatri, Ratna
    Lohner, Rainald
    Verma, Deepanshu
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2021, 2 (01):
  • [44] DOA estimation based on a deep neural network under impulsive noise
    Cai, Ruiyan
    Tian, Quan
    Luo, Yang
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (01) : 785 - 792
  • [45] DOA Estimation Method Based on Improved Deep Convolutional Neural Network
    Zhao, Fangzheng
    Hu, Guoping
    Zhan, Chenghong
    Zhang, Yule
    SENSORS, 2022, 22 (04)
  • [46] DOA Estimation Using Deep Neural Network with Angular Sliding Window
    Li, Yang
    Huang, Zanhu
    Liang, Can
    Zhang, Liang
    Wang, Yanhua
    Wang, Junfu
    Zhang, Yi
    Lv, Hongfen
    ELECTRONICS, 2023, 12 (04)
  • [47] DOA estimation based on a deep neural network under impulsive noise
    Ruiyan Cai
    Quan Tian
    Yang Luo
    Signal, Image and Video Processing, 2024, 18 : 785 - 792
  • [48] Biologically informed deep neural network for prostate cancer discovery
    Haitham A. Elmarakeby
    Justin Hwang
    Rand Arafeh
    Jett Crowdis
    Sydney Gang
    David Liu
    Saud H. AlDubayan
    Keyan Salari
    Steven Kregel
    Camden Richter
    Taylor E. Arnoff
    Jihye Park
    William C. Hahn
    Eliezer M. Van Allen
    Nature, 2021, 598 : 348 - 352
  • [49] Biologically informed deep neural network for prostate cancer discovery
    Elmarakeby, Haitham A.
    Hwang, Justin
    Arafeh, Rand
    Crowdis, Jett
    Gang, Sydney
    Liu, David
    AlDubayan, Saud H.
    Salari, Keyan
    Kregel, Steven
    Richter, Camden
    Arnoff, Taylor E.
    Park, Jihye
    Hahn, William C.
    M. Van Allen, Eliezer
    NATURE, 2021, 598 (7880) : 348 - +
  • [50] Physics-informed deep neural network for image denoising
    Xypakis, Emmanouil
    De Turris, Valeria
    Gala, Fabrizio
    Ruocco, Giancarlo
    Leonetti, Marco
    OPTICS EXPRESS, 2023, 31 (26) : 43838 - 43849