Alternative Pseudo-Labeling for Semi-Supervised Automatic Speech Recognition

被引：2
|
作者：
Zhu, Han [1 ,2 ]
Gao, Dongji [3 ]
Cheng, Gaofeng [1 ,2 ]
Povey, Daniel [4 ]
Zhang, Pengyuan [1 ,2 ]
Yan, Yonghong [1 ,2 ]
机构：
[1] Institute of Acoustics, Chinese Academy of Sciences, Key Laboratory of Speech Acoustics and Content Understanding, Beijing,100190, China
[2] University of Chinese Academy of Sciences, Beijing,100049, China
[3] Johns Hopkins University, Baltimore,MD,21218, United States
[4] Xiaomi Corporation, Beijing,100085, China
来源：
IEEE/ACM Transactions on Audio Speech and Language Processing | 2023年 / 31卷
关键词：
Error detection - Speech recognition;
D O I：
10.1109/TASLP.2023.3306709
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
引用
收藏
页码：3320 / 3330
相关论文
共 50 条
  • [1] Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition
    Higuchi, Yosuke
    Moritz, Niko
    Le Roux, Jonathan
    Hori, Takaaki
    [J]. INTERSPEECH 2021, 2021, : 726 - 730
  • [2] IMPROVED NOISY ITERATIVE PSEUDO-LABELING FOR SEMI-SUPERVISED SPEECH RECOGNITION
    Li, Tian
    Meng, Qingliang
    Sun, Yujian
    [J]. 2022 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP, SLT, 2022, : 167 - 173
  • [3] Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition
    Xu, Yinghao
    Wei, Fangyun
    Sun, Xiao
    Yang, Ceyuan
    Shen, Yujun
    Dai, Bo
    Zhou, Bolei
    Lin, Stephen
    [J]. 2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 2949 - 2958
  • [4] Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning
    Cascante-Bonilla, Paola
    Tan, Fuwen
    Qi, Yanjun
    Ordonez, Vicente
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 6912 - 6920
  • [5] Semi-Supervised Multimodal Emotion Recognition with Class-Balanced Pseudo-Labeling
    Chen, Haifeng
    Guo, Chujia
    Li, Yan
    Zhang, Peng
    Jiang, Dongmei
    [J]. PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 9556 - 9560
  • [6] Compressed video ensemble based pseudo-labeling for semi-supervised action recognition
    Terao, Hayato
    Noguchi, Wataru
    Iizuka, Hiroyuki
    Yamamoto, Masahito
    [J]. MACHINE LEARNING WITH APPLICATIONS, 2022, 9
  • [7] A Pseudo-labeling Approach to Semi-supervised Organ Segmentation
    Gao, Jianwei
    Xu, Juan
    Fei, Honggao
    [J]. FAST AND LOW-RESOURCE SEMI-SUPERVISED ABDOMINAL ORGAN SEGMENTATION, FLARE 2022, 2022, 13816 : 318 - 326
  • [8] Spatial pseudo-labeling for semi-supervised facies classification
    Asghar, Saleem
    Choi, Junhwan
    Yoon, Daeung
    Byun, Joongmoo
    [J]. JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2020, 195
  • [9] Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling
    Feng, Tiantian
    Narayanan, Shrikanth
    [J]. INTERSPEECH 2022, 2022, : 5050 - 5054
  • [10] MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition
    Chen, Xiaodong
    Liu, Wu
    Liu, Xinchen
    Zhang, Yongdong
    Han, Jungong
    Mei, Tao
    [J]. PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2022, 2022,
12345