Lexicon-Based Local Representation for Text-Dependent Speaker Verification

被引：2
|
作者：
You, Hanxu [1 ]
Li, Wei [1 ]
Li, Lianqiang [1 ]
Zhu, Jie [1 ]
机构：
[1] Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
来源：
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2017年 / E100D卷 / 03期
基金：
中国国家自然科学基金;
关键词：
i-vector; L-vector; text-dependent speaker verification; cosine distance kernel;
D O I：
10.1587/transinf.2016EDL8182
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A text-dependent i-vector extraction scheme and a lexicon-based binary vector (L-vector) representation are proposed to improve the performance of text-dependent speaker verification. I-vector and L-vector are used to represent the utterances for enrollment and test. An improved cosine distance kernel is constructed by combining i-vector and L-vector together and is used to distinguish both speaker identity and lexical (or text) diversity with back-end support vector machine (SVM). Experiments are conducted on RSR 2015 Corpus part 1 and part 2, the results indicate that at most 30% improvement can be obtained compared with traditional i-vector baseline.
引用
收藏
页码：587 / 589
页数：3
相关论文
共 50 条
  • [21] Text-dependent Speaker Verification Using Word-based Scoring
    Yao, Shengyu
    Huang, Houjun
    Zhou, Ruohua
    Yan, Yonghong
    2018 11TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2018, : 314 - 318
  • [22] Data Augmentation Enhanced Speaker Enrollment for Text-dependent Speaker Verification
    Sarkar, Achintya Kumar
    Sarma, Himangshu
    Dwivedi, Priyanka
    Tan, Zheng-Hua
    2020 3RD INTERNATIONAL CONFERENCE ON ENERGY, POWER AND ENVIRONMENT: TOWARDS CLEAN ENERGY TECHNOLOGIES (ICEPE 2020), 2021,
  • [23] Template-matching for text-dependent speaker verification
    Dey, Subhadeep
    Motlicek, Petr
    Madikeri, Srikanth
    Ferras, Marc
    SPEECH COMMUNICATION, 2017, 88 : 96 - 105
  • [24] DEEP NEURAL NETWORK BASED POSTERIORS FOR TEXT-DEPENDENT SPEAKER VERIFICATION
    Dey, Subhadeep
    Madikeri, Srikanth
    Ferras, Marc
    Modicek, Petr
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5050 - 5054
  • [25] End-to-End Text-Dependent Speaker Verification
    Heigold, Georg
    Moreno, Ignacio
    Bengio, Samy
    Shazeer, Noam
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5115 - 5119
  • [26] MODELLING THE ALTERNATIVE HYPOTHESIS FOR TEXT-DEPENDENT SPEAKER VERIFICATION
    Larcher, Anthony
    Lee, Kong Aik
    Ma, Bin
    Li, Haizhou
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [27] On Residual CNN in Text-Dependent Speaker Verification Task
    Malykh, Egor
    Novoselov, Sergey
    Kudashev, Oleg
    SPEECH AND COMPUTER, SPECOM 2017, 2017, 10458 : 593 - 601
  • [28] DNN BASED SPEAKER EMBEDDING USING CONTENT INFORMATION FOR TEXT-DEPENDENT SPEAKER VERIFICATION
    Dey, Subhadeep
    Koshinaka, Takafumi
    Motlicek, Petr
    Madikeri, Srikanth
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5344 - 5348
  • [29] Constrained temporal structure for text-dependent speaker verification
    Larcher, Anthony
    Bonastre, Jean-Francois
    Mason, John S. D.
    DIGITAL SIGNAL PROCESSING, 2013, 23 (06) : 1910 - 1917
  • [30] On Training Targets and Activation Functions for Deep Representation Learning in Text-Dependent Speaker Verification
    Sarkar, Achintya Kumar
    Tan, Zheng-Hua
    ACOUSTICS, 2023, 5 (03): : 693 - 713
12345