Modulation Spectrogram Features for Improved Speaker Diarization

被引：0
|
作者：
Vinyals, Oriol [1 ]
Friedland, Gerald [1 ]
机构：
[1] Univ Calif Berkeley, Berkeley, CA 94720 USA
来源：
INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5 | 2008年
关键词：
modulation spectrogram; speaker diarization;
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 propose the use of modulation spectrogram features in speaker diarization. These features carry longer term characteristics of the acoustic signals than the widely used MFCCs, thus providing potential improvement by using both features in combination. Using the state-of-the-art ICSI speaker diarization system, an improvement of 20.77% relative DER is obtained on the MIST Rich Transcription 2007 task with respect to the MFCC only system.
引用
收藏
页码：630 / +
页数：2
相关论文
共 50 条
  • [1] Improved Location Features for Meeting Speaker Diarization
    Otterson, Scott
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2928 - 2931
  • [2] An Improved Speaker Diarization System
    Fu, Rong
    Benest, Ian D.
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1253 - 1256
  • [3] FUSING SHORT TERM AND LONG TERM FEATURES FOR IMPROVED SPEAKER DIARIZATION
    Friedland, A. Gerald
    Vinyals, B. Oriol
    Huang, C. Yan
    Mueller, D. Christian
    2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 4077 - +
  • [4] Factor Analysis for Speaker Segmentation and Improved Speaker Diarization
    Desplanques, Brecht
    Demuynck, Kris
    Martens, Jean-Pierre
    16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 3081 - 3085
  • [5] IMPROVED SPEAKER DIARIZATION SYSTEM FOR MEETINGS
    El-Khoury, Elie
    Senac, Christine
    Pinquier, Julien
    2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 4097 - 4100
  • [6] Prosodic and Phonetic Features for Speaker Clustering in Speaker Diarization Systems
    Zibert, Janez
    Mihelic, France
    12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 1040 - +
  • [7] Harmonic Structure Features for Robust Speaker Diarization
    Zhou, Yu
    Suo, Hongbin
    Li, Junfeng
    Yan, Yonghong
    ETRI JOURNAL, 2012, 34 (04) : 583 - 590
  • [8] FILTERBANK SLOPE BASED FEATURES FOR SPEAKER DIARIZATION
    Madikeri, Srikanth
    Bourlard, Herve
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [9] System output combination for improved speaker diarization
    Bozonnet, Simon
    Evans, Nicholas
    Anguera, Xavier
    Vinyals, Oriol
    Friedland, Gerald
    Fredouille, Corinne
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2650 - +
  • [10] ARTIFICIAL NEURAL NETWORK FEATURES FOR SPEAKER DIARIZATION
    Yella, Harsha
    Stolcke, Andreas
    Slaney, Malcolm
    2014 IEEE WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGY SLT 2014, 2014, : 402 - 406
12345