An Adaptive X-vector Model for Text-independent Speaker Verification

被引:4
|
作者
Gu, Bin [1 ]
Guo, Wu [1 ]
Ding, Penguin [1 ]
Ling, Zhenhua [1 ]
Du, Jun [1 ]
机构
[1] Univ Sci & Technol China, Natl Engn Lab Speech & Language Informat Proc, Hefei, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
Speaker verification; Adaptive convolution; Adaptive batch normalization; Attention mechanism;
D O I
10.21437/Interspeech.2020-1071
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
In this paper, adaptive mechanisms are applied in deep neural network (DNN) training for x-vector-based text-independent speaker verification. First, adaptive convolutional neural networks (ACNNs) are employed in frame-level embedding layers, where the parameters of the convolution filters are adjusted based on the input features. Compared with conventional CNNs, ACNNs have more flexibility in capturing speaker information. Moreover, we replace conventional batch normalization (BN) with adaptive batch normalization (ABN). By dynamically generating the scaling and shifting parameters in BN, ABN adapts models to the acoustic variability arising from various factors such as channel and environmental noises. Finally, we incorporate these two methods to further improve performance. Experiments are carried out on the speaker in the wild (SITW) and VOiCES databases. The results demonstrate that the proposed methods significantly outperform the original x-vector approach.
引用
收藏
页码:1506 / 1510
页数:5
相关论文
共 50 条
  • [11] A tutorial on text-independent speaker verification
    Bimbot, F
    Bonastre, JF
    Fredouille, C
    Gravier, G
    Magrin-Chagnolleau, I
    Meignier, S
    Merlin, T
    Ortega-García, J
    Petrovska-Delacrétaz, D
    Reynolds, DA
    EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2004, 2004 (04) : 430 - 451
  • [12] A Tutorial on Text-Independent Speaker Verification
    Frédéric Bimbot
    Jean-François Bonastre
    Corinne Fredouille
    Guillaume Gravier
    Ivan Magrin-Chagnolleau
    Sylvain Meignier
    Teva Merlin
    Javier Ortega-García
    Dijana Petrovska-Delacrétaz
    Douglas A. Reynolds
    EURASIP Journal on Advances in Signal Processing, 2004
  • [13] Improving X-vector and PLDA for Text-dependent Speaker Verification
    Chen, Zhuxin
    Lin, Yue
    INTERSPEECH 2020, 2020, : 726 - 730
  • [14] GENERATIVE X-VECTORS FOR TEXT-INDEPENDENT SPEAKER VERIFICATION
    Xu, Longting
    Das, Rohan Kumar
    Yilmaz, Emre
    Yang, Jichen
    Li, Haizhou
    2018 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY (SLT 2018), 2018, : 1014 - 1020
  • [15] Vector-Based Attentive Pooling for Text-Independent Speaker Verification
    Wu, Yanfeng
    Guo, Chenkai
    Gao, Hongcan
    Hou, Xiaolei
    Xu, Jing
    INTERSPEECH 2020, 2020, : 936 - 940
  • [16] Context-adaptive Gaussian Attention for Text-independent Speaker Verification
    Peng, Junyi
    Gu, Rongzhi
    Zhang, Haoran
    Zou, Yuexian
    2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 595 - 599
  • [17] A novel text-independent speaker verification method based on the global speaker model
    Zhang, YY
    Zhang, D
    Zhu, XY
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2000, 30 (05): : 598 - 602
  • [18] Graphical models for text-independent speaker verification
    Sánchez-Soto, E
    Sigelle, M
    Chollet, G
    NONLINEAR SPEECH MODELING AND APPLICATIONS, 2005, 3445 : 410 - 415
  • [20] Language dependency in text-independent speaker verification
    Auckenthaler, R
    Carey, MJ
    Mason, JSD
    2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING, 2001, : 441 - 444