Constrained Cepstral Speaker Recognition Using Matched UBM and JFA Training

被引：0
|
作者：
Sanchez, Michelle Hewlett [1 ]
Ferrer, Luciana [1 ]
Shriberg, Elizabeth [1 ]
Stolcke, Andreas [1 ]
机构：
[1] SRI Int, Speech Technol & Res Lab, Menlo Pk, CA 94025 USA
来源：
12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5 | 2011年
关键词：
Speaker Recognition; Cepstral Features; Constraints; Joint Factor Analysis;
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：
We study constrained speaker recognition systems, or systems that model standard cepstral features that fall within particular types of speech regions. A question in modeling such systems is whether to constrain universal background model (UBM) training, joint factor analysis (JFA), or both. We explore this question, as well as how to optimize UBM model size, using a corpus of Arabic male speakers. Over a large set of phonetic and prosodic constraints, we find that the performance of a system using constrained JFA and UBM is on average 5.24% better than when using constraint-independent (all frames) JFA and UBM. We find further improvement from optimizing UBM size based on the percentage of frames covered by the constraint.
引用
收藏
页码：148 / 151
页数：4
相关论文
共 50 条
  • [1] LANGUAGE-INDEPENDENT CONSTRAINED CEPSTRAL FEATURES FOR SPEAKER RECOGNITION
    Shriberg, Elizabeth
    Stolcke, Andreas
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5296 - 5299
  • [2] JFA for Speaker Recognition with Random Digit Strings
    Stafylakis, Themos
    Kenny, Patrick
    Alam, Jahangir
    Kockmann, Marcel
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 190 - 194
  • [3] SPEAKER RECOGNITION USING MATCHED FILTERS
    Aronowitz, Hagai
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5555 - 5559
  • [4] Speaker Independent Word Recognition Using Cepstral Distance Measurement
    Pramanik, Arnab
    Raha, Rajorshee
    [J]. INTELLIGENT INFORMATICS, 2013, 182 : 225 - 235
  • [5] A CEPSTRAL BASED SPEAKER RECOGNITION SYSTEM
    SETHURAMAN, R
    GOWDY, JN
    [J]. PROCEEDINGS : THE TWENTY-FIRST SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY, 1989, : 503 - 507
  • [6] JFA-BASED FRONT ENDS FOR SPEAKER RECOGNITION
    Kenny, Patrick
    Stafylakis, Themos
    Ouellet, Pierre
    Alam, Md. Jahangir
    [J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [7] A method of Automatic Speaker Recognition using cepstral features and vectorial quantization
    de Lara, JRC
    [J]. PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS AND APPLICATIONS, PROCEEDINGS, 2005, 3773 : 146 - 153
  • [8] Feature Generator for Speaker Recognition Using the Fusion of Cepstral and Melcepstral Parameters
    Majda, Ewelina
    Dobrowolski, Andrzej P.
    [J]. 2012 JOINT CONFERENCE NEW TRENDS IN AUDIO & VIDEO AND SIGNAL PROCESSING: ALGORITHMS, ARCHITECTURES, ARRANGEMENTS, & APPLICATIONS (NTAV-SPA 2012), 2012, : 203 - 208
  • [9] Wavelet packet cepstral analysis for speaker recognition
    Kinney, A
    Stevens, J
    [J]. THIRTY-SIXTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS - CONFERENCE RECORD, VOLS 1 AND 2, CONFERENCE RECORD, 2002, : 206 - 209
  • [10] Combining Evidences from Mel Cepstral and Cochlear Cepstral Features for Speaker Recognition Using Whispered Speech
    Raikar, Aditya
    Gandhi, Ami
    Patil, Hemant A.
    [J]. TEXT, SPEECH, AND DIALOGUE (TSD 2015), 2015, 9302 : 405 - 413
12345