A real-time trained system for robust speaker verification using relative space of anchor models

被引:2
作者
Naini, Ali Sadeghi [1 ,2 ]
Homayounpour, M. Mehdi [1 ]
Samani, Abbas [2 ,3 ]
机构
[1] Amirkabir Univ Technol, Dept Comp Engn, Lab Intelligent Sound & Speech Proc, Tehran Polytech, Tehran, Iran
[2] Univ Western Ontario, Dept Elect & Comp Engn, London, ON N6A 5B9, Canada
[3] Univ Western Ontario, Dept Med Biophys, London, ON N6A 5C1, Canada
关键词
Speaker verification; Robust; Noisy condition; Real-time training; Relative space; Absolute space; Anchor models; Reference speakers; Eigenspace; Normalization; Orthogonal; RECOGNITION;
D O I
10.1016/j.csl.2009.07.002
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A real-time trained system for robust speaker verification is proposed. This system was developed using a relative space of reference speakers, also referred to as anchor models. The real-time training aspect of the system is based on this relative space's intriguing features and properties. The relative space concept uses relative speaker representation rather than an absolute representation, by comparing the speaker to a set of well-trained reference speakers. The advantage of this approach is that instead of estimating numerous parameters of an absolute model for a speaker, only a few parameters of a model relative to a number of anchor models are estimated. In order to optimize the performance of the proposed system, several techniques were assessed for possible implementation in various blocks of the system. As a result, the best performance was achieved where normalized vector's mutual angle with the Minimum normalization method was applied to speaker verification in conjunction with an orthogonal relative space of virtual reference speakers. In this case, an Equal Error Rate (EER) of 0.12% on 400 test samples of 100 speakers was obtained. In addition to assessment under normal conditions, the developed speaker verification system was also evaluated under abnormal conditions where noisy or telephonic speech sequence contamination was present. Experiments conducted in this case demonstrated that, in most cases, this system outperforms absolute space based systems even with shortened training speech sequences. Another major contribution of this research is the development of a more complex speaker verification system capable of tackling abnormal conditions more effectively. In this case, other interesting features of the relative space approach were employed. For this purpose, a novel enrichment method was developed to construct a relative space of anchor models trained to tackle noise. The results of the experiments conducted in this part of the research demonstrated an excellent ability of this approach to tackle abnormal conditions. Compared to absolute space based system, applying this method in relative space led to lower error rates of speaker verification in all cases even with low SNR values. (C) 2009 Elsevier Ltd. All rights reserved.
引用
收藏
页码:545 / 561
页数:17
相关论文
共 22 条
  • [1] [Anonymous], P INT C ANT BELG
  • [2] Score normalization for text-independent speaker verification systems
    Auckenthaler, R
    Carey, M
    Lloyd-Thomas, H
    [J]. DIGITAL SIGNAL PROCESSING, 2000, 10 (1-3) : 42 - 54
  • [3] Speech recognition using a wavelet packet adaptive network based fuzzy inference system
    Avci, Engin
    Akpolat, Zuhtu Hakan
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2006, 31 (03) : 495 - 503
  • [4] Bijankhan Mahmood, 1994, P AUSTR C SPEECH SCI, P826
  • [5] 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
    [J]. EURASIP JOURNAL ON APPLIED SIGNAL PROCESSING, 2004, 2004 (04) : 430 - 451
  • [6] Support vector machines using GMM supervectors for speaker verification
    Campbell, WM
    Sturim, DE
    Reynolds, DA
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2006, 13 (05) : 308 - 311
  • [7] State-of-the-art performance in text-independent speaker verification through open-source software
    Fauve, Benoit G. B.
    Matrouf, Driss
    Scheffer, Nicolas
    Bonastre, Jean-Francois
    Mason, John S. D.
    [J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (07): : 1960 - 1968
  • [8] Joint factor analysis versus eigenchannels in speaker recognition
    Kenny, Patrick
    Boulianne, Gilles
    Ouellet, Pierre
    Dumouchel, Pierre
    [J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (04): : 1435 - 1447
  • [9] Rapid speaker adaptation in eigenvoice space
    Kuhn, R
    Junqua, JC
    Nguyen, P
    Niedzielski, N
    [J]. IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2000, 8 (06): : 695 - 707
  • [10] Li K.P., 1988, P IEEE INT C ACOUSTI, P595