JOINT TIME-FREQUENCY SCATTERING FOR AUDIO CLASSIFICATION

被引：0
|
作者：
Anden, Joakim [1 ]
Lostanlen, Vincent [2 ]
Mallat, Stephane [2 ]
机构：
[1] Princeton Univ, PACM, Princeton, NJ 08544 USA
[2] Ecole Normale Super, Dept Informat, Paris, France
来源：
2015 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING | 2015年
关键词：
audio classification; invariant descriptors; time-frequency structure; wavelets; convolutional networks;
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 introduce the joint time-frequency scattering transform, a time shift invariant descriptor of time-frequency structure for audio classification. It is obtained by applying a twodimensional wavelet transform in time and log-frequency to a time-frequency wavelet scalogram. We show that this descriptor successfully characterizes complex time-frequency phenomena such as time-varying filters and frequency modulated excitations. State-of-the-art results are achieved for signal reconstruction and phone segment classification on the TIMIT dataset.
引用
收藏
页数：6
相关论文
共 50 条
  • [1] Joint Time-Frequency Scattering
    Anden, Joakim
    Lostanlen, Vincent
    Mallat, Stephane
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2019, 67 (14) : 3704 - 3718
  • [2] Content based audio classification and retrieval using joint time-frequency analysis
    Esmaili, S
    Krishnan, S
    Raahemifar, K
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 665 - 668
  • [3] AUDIO CLASSIFICATION FROM TIME-FREQUENCY TEXTURE
    Yu, Guoshen
    Slotine, Jean-Jacques
    2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 1677 - +
  • [4] Classification of Time-Frequency Regions in Stereo Audio
    Harma, Aki
    JOURNAL OF THE AUDIO ENGINEERING SOCIETY, 2011, 59 (10): : 707 - 720
  • [5] Audio signal classification using time-frequency parameters
    Umapathy, K
    Krishnan, S
    Jimaa, S
    IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOL I AND II, PROCEEDINGS, 2002, : A249 - A252
  • [6] LEARNING SEPARABLE TIME-FREQUENCY FILTERBANKS FOR AUDIO CLASSIFICATION
    Pu, Jie
    Panagakis, Yannis
    Pantic, Maja
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 3000 - 3004
  • [7] TFECN: Time-Frequency Enhanced ConvNet for Audio Classification
    Wang, Mengwei
    Yang, Zhe
    INTERSPEECH 2023, 2023, : 281 - 285
  • [8] Multigroup classification of audio signals using time-frequency parameters
    Umapathy, K
    Krishnan, S
    Jimaa, S
    IEEE TRANSACTIONS ON MULTIMEDIA, 2005, 7 (02) : 308 - 315
  • [9] Enhancing Spectrogram for Audio Classification Using Time-Frequency Enhancer
    Xing, Haoran
    Zhang, Shiqi
    Takeuchi, Daiki
    Niizumi, Daisuke
    Harada, Noboru
    Makino, Shoji
    2023 ASIA PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE, APSIPA ASC, 2023, : 1155 - 1160
  • [10] Time-Frequency Scattergrams for Biomedical Audio Signal Representation and Classification
    Sharma, Garima
    Umapathy, Karthikeyan
    Krishnan, Sridhar
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2024, 32 : 564 - 576
12345