GENERATIVE ADVERSARIAL SOURCE SEPARATION

被引：0
|
作者：
Subakan, Y. Cem [1 ]
Smaragdis, Paris [1 ,2 ]
机构：
[1] UIUC, Urbana, IL 61801 USA
[2] Adobe Syst, San Jose, CA USA
来源：
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2018年
基金：
美国国家科学基金会;
关键词：
Generative Adversarial Networks; Source Separation; Generative Models;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source separation experiment that, a multi-layer perceptron trained with a Wasserstein-GAN formulation outperforms NMF, auto-encoders trained with maximum likelihood, and variational auto-encoders in terms of source to distortion ratio.
引用
收藏
页码：26 / 30
页数：5
相关论文
共 50 条
  • [31] Exploring generative adversarial networks and adversarial training
    Sajeeda A.
    Hossain B.M.M.
    Int. J. Cogn. Comp. Eng., (78-89): : 78 - 89
  • [32] Deep Unfolding Contrast Source Inversion for Strong Scatterers via Generative Adversarial Mechanism
    Zhou, Huilin
    Cheng, Yang
    Zheng, Huimin
    Liu, Qiegen
    Wang, Yuhao
    IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2022, 70 (11) : 4966 - 4979
  • [33] Terrain Rebuilding Method based on Open Source Data and Conditional Generative Adversarial Networks
    Chen K.
    Lei S.
    Dai W.
    Wang C.
    Liu A.
    Li M.
    Journal of Geo-Information Science, 2023, 25 (02) : 252 - 264
  • [34] Multi-Source Medical Image Fusion Based on Wasserstein Generative Adversarial Networks
    Yang, Zhiguang
    Chen, Youping
    Le, Zhuliang
    Fan, Fan
    Pan, Erting
    IEEE ACCESS, 2019, 7 : 175947 - 175958
  • [35] Generative adversarial networks (GAN) for compact beam source modelling in Monte Carlo simulations
    Sarrut, D.
    Krah, N.
    Letang, J. M.
    PHYSICS IN MEDICINE AND BIOLOGY, 2019, 64 (21):
  • [36] Monthly Source and Load Scenario Generation Based on Progressive Growing of Generative Adversarial Nets
    Zhu, Chenzhenghan
    Liu, Dongge
    Huang, Jinju
    Han, Xiaonan
    Gao, Yuan
    Sun, Yingyun
    Gaodianya Jishu/High Voltage Engineering, 2024, 50 (09): : 3955 - 3964
  • [37] Forecasting Taxi Demands Using Generative Adversarial Networks with Multi-Source Data
    Naji, Hasan A. H.
    Xue, Qingji
    Zhu, Huijun
    Li, Tianfeng
    APPLIED SCIENCES-BASEL, 2021, 11 (20):
  • [38] Interpretable Generative Adversarial Networks
    Li, Chao
    Yao, Kelu
    Wang, Jin
    Diao, Boyu
    Xu, Yongjun
    Zhang, Quanshi
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 1280 - 1288
  • [39] Steganographic Generative Adversarial Networks
    Volkhonskiy, Denis
    Nazarov, Ivan
    Burnaev, Evgeny
    TWELFTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2019), 2020, 11433
  • [40] Wasserstein Generative Adversarial Networks
    Arjovsky, Martin
    Chintala, Soumith
    Bottou, Leon
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
12345