Geometric contamination for GMM/UBM speaker verification in reverberant environments

被引:0
作者
Brutti, Alessio [1 ]
Omologo, Maurizio [1 ]
机构
[1] Fdn Bruno Kessler CIT Irst, Via Sommar 18 Trento, Trento, Italy
来源
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5 | 2013年
关键词
speaker verification; distant speech; data contamination;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Reverberation generated by multi-path acoustic propagation in enclosures is one of the most critical issues for distant-speech speaker verification systems. While late arrivals can be treated as additive noise, early reflections critically affects the speech spectral properties that allow differentiating among speakers. Considering a standard GMM/UBM speaker verification system based on MFCC, a geometric data contamination scheme relying on a rough modeling of the sound propagation through the image method is presented to attack the reverberation. The contribution of this paper is twofold: first, an analysis of the amount of knowledge of the impulse response needed for an effective contamination is carried out on simulated data; second, the geometric contamination is applied to real impulse responses to validate its use in real application contexts. Preliminary experimental results are provided to support the theoretical study and show the effectiveness of the approach.
引用
收藏
页码:3632 / 3636
页数:5
相关论文
共 26 条
  • [1] SPEAKER IDENTIFICATION IN ROOM REVERBERATION USING GMM-UBM
    Akula, Aditi
    Apsingekar, Vijendra Raj
    De Leon, Phillip L.
    [J]. 2009 IEEE 13TH DIGITAL SIGNAL PROCESSING WORKSHOP & 5TH IEEE PROCESSING EDUCATION WORKSHOP, VOLS 1 AND 2, PROCEEDINGS, 2009, : 37 - 41
  • [2] IMAGE METHOD FOR EFFICIENTLY SIMULATING SMALL-ROOM ACOUSTICS
    ALLEN, JB
    BERKLEY, DA
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1979, 65 (04) : 943 - 950
  • [3] [Anonymous], P IEEE INSTR MEAS TE
  • [4] Bimbot F., 2004, EURASIP J ADV SIGNAL, V2004
  • [5] An environment aware ML estimation of acoustic radiation pattern with distributed microphone pairs
    Brutti, A.
    Omologo, M.
    Svaizer, P.
    [J]. SIGNAL PROCESSING, 2013, 93 (04) : 784 - 796
  • [6] Brutti A., 2006, INTERSPEECH
  • [7] 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
  • [8] De Leon P.L., 2007, P BIOMETRICS S, P1, DOI [10.1109/BCC.2007.4430544, DOI 10.1109/BCC.2007.4430544]
  • [9] Dehak N, 2009, INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, P1527
  • [10] CEPSTRAL ANALYSIS TECHNIQUE FOR AUTOMATIC SPEAKER VERIFICATION
    FURUI, S
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1981, 29 (02): : 254 - 272