Speaker verification based on adapted Gaussian mixture model feature mapping

被引：0
|
作者：
Department of Electronic Science and Technology, University of Science and Technology of China, Hefei 230027, China [1 ]
机构：
来源：
Moshi Shibie yu Rengong Zhineng | 2009年 / 3卷 / 417-421期
关键词：
Gaussian distribution - Speech recognition;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
To mitigate the channel effect of the handset speaker recognition system, a feature mapping (FM) method is proposed to eliminate the channel variability. Gaussian mixture model (GMM) is used to establish a channel-independent voice model, and the channel-dependent voice models are derived from the GMM using a well-known maximum a posteriori (MAP) adaptation algorithm. The difference of clustering gaussians describes the channel variability for different voice. The mismatch between train and test is compensated by mapping channel rules. Experimental results on NIST99 and 2004 SRE database show that the system performance can be increased by 14.7% and 15.18% by the proposed approach.
引用
收藏
相关论文
共 50 条
  • [31] Research of the speaker verification based on the SVM-GMM mixture model
    Xuan, Cui
    Bo, Deng
    Wen, Zhuang
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS AND KNOWLEDGE ENGINEERING (ISKE 2007), 2007,
  • [32] Automatic speaker verification from affective speech using Gaussian mixture model based estimation of neutral speech characteristics
    Avila, Anderson R.
    O'Shaughnessy, Douglas
    Falk, Tiago H.
    SPEECH COMMUNICATION, 2021, 132 : 21 - 31
  • [33] A comparison of Gaussian Mixture and Multiple Binary Classifier Models for speaker verification
    Slomka, S
    Castellano, P
    Barger, P
    Sridharan, S
    Narasimhan, VL
    ANZIIS 96 - 1996 AUSTRALIAN NEW ZEALAND CONFERENCE ON INTELLIGENT INFORMATION SYSTEMS, PROCEEDINGS, 1996, : 316 - 319
  • [34] Speaker verification using text-constrained Gaussian mixture models
    Sturim, DE
    Reynolds, DA
    Dunn, RB
    Quatieri, TF
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 677 - 680
  • [35] Forensic Speaker Verification Using Formant Features and Gaussian Mixture Models
    Becker, Timo
    Jessen, Michael
    Grigoras, Catalin
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1505 - +
  • [36] Quantization for adapted GMM-based speaker verification
    Tseng, Ivy H.
    Verscheure, Olivier
    Turaga, Deepak S.
    Chaudhari, Upendra V.
    2006 IEEE International Conference on Acoustics, Speech and Signal Processing, Vols 1-13, 2006, : 653 - 656
  • [37] Phoneme based speaker verification by Gaussian mixture models with adaptation of subsets of dominant parameters and phonemes
    Gutman, D
    Bistritz, Y
    22ND CONVENTION OF ELECTRICAL AND ELECTRONICS ENGINEERS IN ISRAEL, PROCEEDINGS, 2002, : 246 - 246
  • [38] Channel robust speaker verification via extended feature mapping
    Fu, ZH
    Lei, X
    Zhao, RC
    2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3, 2004, : 2417 - 2420
  • [39] Combining Gaussian mixture models and segmental feature models for speaker recognition
    Milosevic, Milana
    Glavitsch, Ulrike
    18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 2042 - 2043
  • [40] Improved Gaussian Mixture Model and Application in Speaker Recognition
    Bao Lingling
    Shen Xizhong
    PROCEEDINGS OF 2016 THE 2ND INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND ROBOTICS, 2016, : 387 - 390
12345