Large-Scale Domain Adaptation via Teacher-Student Learning

被引:48
|
作者
Li, Jinyu [1 ]
Seltzer, Michael L. [1 ]
Wang, Xi [1 ]
Zhao, Rui [1 ]
Gong, Yifan [1 ]
机构
[1] Microsoft AI & Res, One Microsoft Way, Redmond, WA 98052 USA
来源
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION | 2017年
关键词
teacher-student learning; parallel unlabeled data; SPEECH RECOGNITION;
D O I
10.21437/Interspeech.2017-519
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually requires significant labeled data from the target domain. In this work, we propose an approach to domain adaptation that does not require transcriptions but instead uses a corpus of unlabeled parallel data, consisting of pairs of samples from the source domain of the well-trained model and the desired target domain. To perform adaptation, we employ teacher/student (T/S) learning, in which the posterior probabilities generated by the source-domain model can be used in lieu of labels to train the target-domain model. We evaluate the proposed approach in two scenarios, adapting a clean acoustic model to noisy speech and adapting an adults' speech acoustic model to children's speech. Significant improvements in accuracy are obtained, with reductions in word error rate of up to 44% over the original source model without the need for transcribed data in the target domain. Moreover, we show that increasing the amount of unlabeled data results in additional model robustness. which is particularly beneficial when using simulated training data in the target-domain.
引用
收藏
页码:2386 / 2390
页数:5
相关论文
共 50 条
  • [1] ADVERSARIAL TEACHER-STUDENT LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
    Meng, Zhong
    Li, Jinyu
    Gong, Yifan
    Juang, Biing-Hwang
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5949 - 5953
  • [2] DOMAIN ADAPTATION VIA TEACHER-STUDENT LEARNING FOR END-TO-END SPEECH RECOGNITION
    Meng, Zhong
    Li, Jinyu
    Gaur, Yashesh
    Gong, Yifan
    2019 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU 2019), 2019, : 268 - 275
  • [3] Unsupervised Teacher-Student Model for Large-scale Video Retrieval
    Liang, Dong
    Lin, Lanfen
    Wang, Rui
    Shao, Jie
    Wang, Changhu
    Chen, Yen-Wei
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW), 2019, : 1863 - 1867
  • [4] PROGRESSIVE MIXUP AUGMENTED TEACHER-STUDENT LEARNING FOR UNSUPERVISED DOMAIN ADAPTATION
    Zheng, Aotian
    Mei, Jie
    Wallace, Farron
    Rose, Craig
    Hussein, Rania
    Hwang, Jenq-Neng
    2023 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP, 2023, : 3030 - 3034
  • [5] Robust Speech Recognition Using Teacher-Student Learning Domain Adaptation
    Ma, Han
    Zhang, Qiaoling
    Tang, Roubing
    Zhang, Lu
    Jia, Yubo
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2022, E105D (12) : 2112 - 2118
  • [6] Teacher-Student Competition for Unsupervised Domain Adaptation
    Xiao, Ruixin
    Liu, Zhilei
    Wu, Baoyuan
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 8291 - 8298
  • [7] Exploiting Large-Scale Teacher-Student Training for On-Device Acoustic Models
    Liu, Jing
    Swaminathan, Rupak Vignesh
    Parthasarathi, Sree Hari Krishnan
    Lyu, Chunchuan
    Mouchtaris, Athanasios
    Kunzmann, Siegfried
    TEXT, SPEECH, AND DIALOGUE, TSD 2021, 2021, 12848 : 413 - 424
  • [8] FACILITATING TEACHER-STUDENT COMMUNICATION AND INTERACTION IN LARGE-SCALE LECTURES WITH SMARTPHONES AND RWTHAPP
    Politze, M.
    Decker, B.
    Schaffert, S.
    Kueppers, B.
    EDULEARN15: 7TH INTERNATIONAL CONFERENCE ON EDUCATION AND NEW LEARNING TECHNOLOGIES, 2015, : 4820 - 4828
  • [9] Simulation-to-real domain adaptation with teacher-student learning for endoscopic instrument segmentation
    Sahu, Manish
    Mukhopadhyay, Anirban
    Zachow, Stefan
    INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2021, 16 (05) : 849 - 859
  • [10] Teacher-Student Mutual Learning for efficient source-free unsupervised domain adaptation
    Li, Wei
    Fan, Kefeng
    Yang, Huihua
    KNOWLEDGE-BASED SYSTEMS, 2023, 261