Maximum Gaussianality training for deep speaker vector normalization

被引：0
|
作者：
Cai, Yunqi [1 ,2 ,3 ]
Li, Lantian [4 ]
Abel, Andrew [5 ]
Zhu, Xiaoyan [3 ]
Wang, Dong [2 ]
机构：
[1] Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming,650504, China
[2] Center for Speech, and Language Technologies (CSLT), BNRist at Tsinghua University, Beijing,100084, China
[3] Department of Computer Science at Tsinghua University, Beijing,100084, China
[4] Artificial Intelligence at Beijing University of Posts and Telecommunications, Beijing, China
[5] Computer and Information Sciences, University of Strathclyde, Glasgow, Scotland, United Kingdom
来源：
Pattern Recognition | 2024年 / 145卷
关键词：
Compendex;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Embeddings - Speech recognition
引用
收藏
相关论文
共 50 条
  • [1] Maximum Gaussianality training for deep speaker vector normalization
    Cai, Yunqi
    Li, Lantian
    Abel, Andrew
    Zhu, Xiaoyan
    Wang, Dong
    PATTERN RECOGNITION, 2024, 145
  • [2] Speaker adaptive training: A maximum likelihood approach to speaker normalization
    Anastasakos, T
    McDonough, J
    Makhoul, J
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 1043 - 1046
  • [3] Deep Normalization for Speaker Vectors
    Cai, Yunqi
    Li, Lantian
    Abel, Andrew
    Zhu, Xiaoyan
    Wang, Dong
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 : 733 - 744
  • [4] A study on speaker normalization using vocal tract normalization and speaker adaptive training
    Welling, L
    Haeb-Umbach, R
    Aubert, X
    Haberland, N
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 797 - 800
  • [5] DEEP NEURAL NETWORK TRAINED WITH SPEAKER REPRESENTATION FOR SPEAKER NORMALIZATION
    Tang, Yun
    Mohan, Aanchan
    Rose, Richard C.
    Ma, Chengyuan
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [6] Speaker retrieval based on deep speaker vector
    Li, Wei
    Yang, Jichen
    He, Qianhua
    Li, Yanxiong
    Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition), 2015, 43 (07): : 62 - 65
  • [7] A vector-quantizer based method of speaker normalization
    Shin, OK
    Fourth Annual ACIS International Conference on Computer and Information Science, Proceedings, 2005, : 402 - 407
  • [8] Speaker-Independent Silent Speech Recognition with Across-Speaker Articulatory Normalization and Speaker Adaptive Training
    Wang, Jun
    Hahm, Seongjun
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2415 - 2419
  • [9] Comparison of vector normalization methods in multi-level speaker verification
    Drgas, Szymon
    Dabrowski, Adam
    2012 INTERNATIONAL CONFERENCE ON SIGNALS AND ELECTRONIC SYSTEMS (ICSES), 2012,
  • [10] Analysis of I-vector Length Normalization in Speaker Recognition Systems
    Garcia-Romero, Daniel
    Espy-Wilson, Carol Y.
    12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 256 - 259
12345