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
  • [21] AN ADAPTIVE INITIALIZATION METHOD FOR SPEAKER DIARIZATION BASED ON PROSODIC FEATURES
    Imseng, David
    Friedland, Gerald
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4946 - 4949
  • [22] 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
  • [23] Overlapped speech detection for improved speaker diarization in multiparty meetings
    Boakye, Kofi
    Trueba-Hornero, Beatriz
    Vinyals, Oriol
    Friedland, Gerald
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4353 - 4356
  • [24] Overlap Detection for Speaker Diarization by Fusing Spectral and Spatial Features
    Zelenak, Martin
    Segura, Carlos
    Hernando, Javier
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2302 - 2305
  • [25] An Information Theoretic Combination of MFCC and TDOA Features for Speaker Diarization
    Vijayasenan, Deepu
    Valente, Fabio
    Bourlard, Herve
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2011, 19 (02): : 431 - 438
  • [26] Statistical Speaker Diarization Using Dependent Combination of Extracted Features
    Almgotir-Kadhimi, Hasan
    Woo, Lok
    Dlay, Satnam
    2015 THIRD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, MODELLING AND SIMULATION (AIMS 2015), 2015, : 291 - 296
  • [27] SPEAKER DIARIZATION THROUGH SPEAKER EMBEDDINGS
    Rouvier, Mickael
    Bousquet, Pierre-Michel
    Favre, Benoit
    2015 23RD EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2015, : 2082 - 2086
  • [28] Multimodal Speaker Diarization
    Noulas, Athanasios
    Englebienne, Gwenn
    Krose, Ben J. A.
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (01) : 79 - 93
  • [29] SPEAKER DIARIZATION WITH LSTM
    Wang, Quan
    Downey, Carlton
    Wan, Li
    Mansfield, Philip Andrew
    Moreno, Ignacio Lopez
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5239 - 5243
  • [30] Trainable Speaker Diarization
    Aronowitz, Hagai
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2021 - 2024
12345