Long span prosodic features for speaker recognition

被引：0
|
作者：
Zhang, Jianping [1 ]
Li, Ming [1 ]
Suo, Hongbin [1 ]
Yang, Lin [1 ]
Fu, Qiang [1 ]
Yan, Yonghong [1 ]
机构：
[1] ThinkIT Speech Lab., Chinese Acad. of Sci., Beijing 100190, China
来源：
Shengxue Xuebao/Acta Acustica | 2010年 / 35卷 / 02期
关键词：
Continuous speech recognition - Polynomial approximation;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, we first give an introduction about speaker recognition techniques. Then a novel speaker verification method based on long span prosodic features is proposed. After speech is pre-processed by a voice activity detection module, and basic prosody features are extracted for each speech unit, we carried out an approximation of the pitch, formant, time domain energy and harmonic energy contours by taking the leading terms in a Legendre polynomial expansion. HLDA is used to reduce the feature dimension and mean supervector in each individual Gaussian is used to represent the distribution of the time-frequency features. Experiments on NIST06 show that the proposed method can reduce the EER from 4.9% to 4.6% when fusing with the traditional MFCC-featured system. © Right.
引用
收藏
页码：267 / 269
相关论文
共 50 条
  • [1] Speaker recognition using prosodic and lexical features
    Kajarekar, S
    Ferrer, L
    Venkataraman, A
    Sonmez, K
    Shriberg, E
    Stolcke, A
    Bratt, H
    Gadde, RR
    ASRU'03: 2003 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING ASRU '03, 2003, : 19 - 24
  • [2] A COMPARISON OF APPROACHES FOR MODELING PROSODIC FEATURES IN SPEAKER RECOGNITION
    Ferrer, Luciana
    Scheffer, Nicolas
    Shriberg, Elizabeth
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4414 - 4417
  • [3] CONTOUR MODELING OF PROSODIC AND ACOUSTIC FEATURES FOR SPEAKER RECOGNITION
    Kockmann, Marcel
    Burget, Lukas
    2008 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY: SLT 2008, PROCEEDINGS, 2008, : 45 - 48
  • [4] Extraction and representation of prosodic features for language and speaker recognition
    Mary, Leena
    Yegnanarayana, B.
    SPEECH COMMUNICATION, 2008, 50 (10) : 782 - 796
  • [5] INVESTIGATIONS INTO PROSODIC SYLLABLE CONTOUR FEATURES FOR SPEAKER RECOGNITION
    Kockmann, Marcel
    Burget, Lukas
    Cernocky, Jan Honza
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4418 - 4421
  • [6] Improvement of speaker recognition by combining residual and prosodic features with acoustic features
    Chen, SH
    Wang, HC
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 93 - 96
  • [7] Automatic speaker recognition using LVQ with 3 prosodic features
    Ouamour-Sayoud, S
    Sayoud, H
    INTELLIGENT AND ADAPTIVE SYSTEMS AND SOFTWARE ENGINEERING, 2004, : 95 - 99
  • [8] Prosodic and other Long-Term Features for Speaker Diarization
    Friedland, Gerald
    Vinyals, Oriol
    Huang, Yan
    Mueller, Christian
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2009, 17 (05): : 985 - 993
  • [9] Prosodic Features for Speaker Verification
    Mary, Leena
    Yegnanarayana, B.
    INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 917 - 920
  • [10] Speaker overlap detection with prosodic features for speaker diarisation
    Zelenak, M.
    Hernando, J.
    IET SIGNAL PROCESSING, 2012, 6 (08) : 798 - 804
12345