Speech Enhancement Network with Unsupervised Attention using Invariant Information Clustering

被引:0
|
作者
Sugiura, Yosuke [1 ]
Nagamori, Shunta [1 ]
Shimamura, Tetsuya [1 ]
机构
[1] Saitama Univ, Fac Engn, Saitama, Japan
关键词
GENERATIVE ADVERSARIAL NETWORKS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose a new framework for speech enhancement using supervised attention trained by Invariant Information Clustering (IIC). For suppressing an overfitting in the speech enhancement network, the multitask learning with the speaker-invariant information is adopted at the latent representation layer. Several simulations reveal the effectiveness of this method through the speech enhancement experiments.
引用
收藏
页码:406 / 409
页数:4
相关论文
共 50 条
  • [1] Unsupervised Cell Segmentation by Invariant Information Clustering
    van Nierop, Wessel L.
    Schneider, Jan-N.
    de With, Peter H. N.
    van der Sommen, Fons
    [J]. MEDICAL IMAGING 2024: IMAGE PROCESSING, 2024, 12926
  • [2] Invariant Information Clustering for Unsupervised Image Classification and Segmentation
    Ji, Xu
    Henriques, Joao F.
    Vedaldi, Andrea
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9864 - 9873
  • [3] LE-GAN: Unsupervised low-light image enhancement network using attention module and identity invariant loss
    Fu, Ying
    Hong, Yang
    Chen, Linwei
    You, Shaodi
    [J]. KNOWLEDGE-BASED SYSTEMS, 2022, 240
  • [4] Neural Comb Filtering Using Sliding Window Attention Network for Speech Enhancement
    Venkatesh Parvathala
    Sivaganesh Andhavarapu
    Giridhar Pamisetty
    K. Sri Rama Murty
    [J]. Circuits, Systems, and Signal Processing, 2023, 42 : 322 - 343
  • [5] Neural Comb Filtering Using Sliding Window Attention Network for Speech Enhancement
    Parvathala, Venkatesh
    Andhavarapu, Sivaganesh
    Pamisetty, Giridhar
    Murty, K. Sri Rama
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2023, 42 (01) : 322 - 343
  • [6] Unsupervised Speech Enhancement Using Optimal Transport and Speech Presence Probability
    Jiang, Wenbin
    Yu, Kai
    Wen, Fei
    [J]. IEEE/ACM Transactions on Audio Speech and Language Processing, 2024, 32 : 4445 - 4455
  • [7] A Recursive Network with Dynamic Attention for Monaural Speech Enhancement
    Li, Andong
    Zheng, Chengshi
    Fan, Cunhang
    Peng, Renhua
    Li, Xiaodong
    [J]. INTERSPEECH 2020, 2020, : 2422 - 2426
  • [8] Speech Enhancement of Complex Convolutional Recurrent Network with Attention
    Jiangjiao Zeng
    Lidong Yang
    [J]. Circuits, Systems, and Signal Processing, 2023, 42 : 1834 - 1847
  • [9] Speech Enhancement of Complex Convolutional Recurrent Network with Attention
    Zeng, Jiangjiao
    Yang, Lidong
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2022, 42 (3) : 1834 - 1847
  • [10] Unsupervised Speech Enhancement Using Dynamical Variational Autoencoders
    Bie, Xiaoyu
    Leglaive, Simon
    Alameda-Pineda, Xavier
    Girin, Laurent
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 30 : 2993 - 3007