Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition

被引:0
|
作者
Inoue, Nakamasa [1 ]
Goto, Keita [1 ]
机构
[1] Tokyo Inst Technol, Tokyo, Japan
基金
日本学术振兴会; 日本科学技术振兴机构;
关键词
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
This paper introduces a semi-supervised contrastive learning framework and its application to text-independent speaker verification. The proposed framework employs generalized contrastive loss (GCL). GCL unifies losses from two different learning frameworks, supervised metric learning and unsupervised contrastive learning, and thus it naturally determines the loss for semi-supervised learning. In experiments, we applied the proposed framework to text-independent speaker verification on the VoxCeleb dataset. We demonstrate that GCL enables the learning of speaker embeddings in three manners, supervised learning, semi-supervised learning, and unsupervised learning, without any changes in the definition of the loss function.
引用
收藏
页码:1641 / 1646
页数:6
相关论文
共 50 条
  • [1] Semi-Supervised Contrastive Learning for Human Activity Recognition
    Liu, Dongxin
    Abdelzaher, Tarek
    [J]. 17TH ANNUAL INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING IN SENSOR SYSTEMS (DCOSS 2021), 2021, : 45 - 53
  • [2] Semi-Supervised Action Recognition with Temporal Contrastive Learning
    Singh, Ankit
    Chakraborty, Omprakash
    Varshney, Ashutosh
    Panda, Rameswar
    Feris, Rogerio
    Saenko, Kate
    Das, Abir
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 10384 - 10394
  • [3] CONTRASTIVE SEMI-SUPERVISED LEARNING FOR ASR
    Xiao, Alex
    Fuegen, Christian
    Mohamed, Abdelrahman
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 3870 - 3874
  • [4] Contrastive Regularization for Semi-Supervised Learning
    Lee, Doyup
    Kim, Sungwoong
    Kim, Ildoo
    Cheon, Yeongjae
    Cho, Minsu
    Han, Wook-Shin
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 3910 - 3919
  • [5] Semi-Supervised Group Emotion Recognition Based on Contrastive Learning
    Zhang, Jiayi
    Wang, Xingzhi
    Zhang, Dong
    Lee, Dah-Jye
    [J]. ELECTRONICS, 2022, 11 (23)
  • [6] Actor-Aware Contrastive Learning for Semi-Supervised Action Recognition
    Assefa, Maregu
    Jiang, Wei
    Gedamu, Kumie
    Yilma, Getinet
    Ayalew, Melese
    Seid, Mohammed
    [J]. 2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 660 - 665
  • [7] A Probabilistic Contrastive Framework for Semi-Supervised Learning
    Lin, Huibin
    Zhang, Chun-Yang
    Wang, Shiping
    Guo, Wenzhong
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 8767 - 8779
  • [8] CONTRASTIVE SIAMESE NETWORK FOR SEMI-SUPERVISED SPEECH RECOGNITION
    Khorram, Soheil
    Kim, Jaeyoung
    Tripathi, Anshuman
    Lu, Han
    Zhang, Qian
    Sak, Hasim
    [J]. 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 7207 - 7211
  • [9] Uncertainty-Aware Contrastive Learning for semi-supervised named entity recognition
    Yang, Kang
    Yang, Zhiwei
    Zhao, Songwei
    Yang, Zhejian
    Zhang, Sinuo
    Chen, Hechang
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 296
  • [10] Neighbor-Guided Consistent and Contrastive Learning for Semi-Supervised Action Recognition
    Wu, Jianlong
    Sun, Wei
    Gan, Tian
    Ding, Ning
    Jiang, Feijun
    Shen, Jialie
    Nie, Liqiang
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 2215 - 2227