ACOUSTIC SCENE CLASSIFICATION WITH MISMATCHED RECORDING DEVICES USING MIXTURE OF EXPERTS LAYER

被引:11
|
作者
Truc Nguyen [1 ]
Pernkopf, Franz [1 ]
机构
[1] Graz Univ Technol, Signal Proc & Speech Commun Lab, Inffeldgasse 16c, A-8010 Graz, Austria
来源
2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) | 2019年
基金
奥地利科学基金会;
关键词
Acoustic scene classification; convolutional neural network; mixture of experts layer; mixture of softmaxes;
D O I
10.1109/ICME.2019.00287
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Recently, a mismatch in acoustic conditions such as a temporal recording gap as well as different recording devices for the development and the evaluation data has been considered in Acoustic Scene Classification (ASC). This brings ASC closer to real world conditions. In this paper, we address ASC with mismatching recording devices. This has been introduced as task 1B of the DCASE 2018 challenge. We proposed a flexible and robust model that uses a mixture of experts (MoE) layer replacing the fully connected dense layer such that each expert can adapt to the specific domains of the data. Furthermore, we observe different Convolutional Neural Network (CNN) models as well as the number of the experts of the MoE dense layer using log-mel features. In addition, we perform mixup data augmentation to enhance the robustness of our models. In experiments, the classification performance is 66.1% using 15 experts in the MoE dense layer with approximately 2M parameters. This outperforms the best model of task 1B of the DCASE 2018 challenge by 2.5% (absolute). This model uses an ensemble selection of 12 individual models with similar to 12M parameters.
引用
收藏
页码:1666 / 1671
页数:6
相关论文
共 50 条
  • [21] Mixture of CNN Experts from Multiple Acoustic Feature Domain for Music Genre Classification
    Yi, Yang
    Chen, Kuan-Yu
    Gu, Hung-Yan
    2019 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2019, : 1250 - 1255
  • [22] A Layer-wise Score Level Ensemble Framework for Acoustic Scene Classification
    Singh, Arshdeep
    Thakur, Anshul
    Rajan, Padmanabhan
    Bhavsar, Arnav
    2018 26TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2018, : 837 - 841
  • [23] A Comparative Study on Approaches to Acoustic Scene Classification Using CNNs
    Ananya, Ishrat Jahan
    Suad, Sarah
    Choudhury, Shadab Hafiz
    Khan, Mohammad Ashrafuzzaman
    ADVANCES IN COMPUTATIONAL INTELLIGENCE (MICAI 2021), PT I, 2021, 13067 : 81 - 91
  • [24] Acoustic scene classification using projection Kervolutional neural network
    Mulimani, Manjunath
    Nandi, Ritika
    Koolagudi, Shashidhar G.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (06) : 9447 - 9457
  • [25] Acoustic scene classification using pixel-based attention
    WANG X.
    XU Y.
    SHI J.
    TENG X.
    AES: Journal of the Audio Engineering Society, 2020, 68 (11): : 843 - 855
  • [26] Acoustic Scene Classification Using Pixel-Based Attention
    Wang, Xingmei
    Xu, Yichao
    Shi, Jiahao
    Teng, Xuyang
    JOURNAL OF THE AUDIO ENGINEERING SOCIETY, 2020, 68 (11): : 843 - 855
  • [27] Acoustic scene classification using projection Kervolutional neural network
    Manjunath Mulimani
    Ritika Nandi
    Shashidhar G Koolagudi
    Multimedia Tools and Applications, 2023, 82 : 9447 - 9457
  • [28] Classification in mixture of experts using hard clustering and a new gate function
    Bulut, Faruk
    Amasyali, M. Fatih
    JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY, 2016, 31 (04): : 1017 - 1025
  • [29] Acoustic Scene Classification using Binaural Representation and Classifier Combination
    Arabnezhad, Fatemeh
    Nasersharif, Babak
    2019 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND KNOWLEDGE ENGINEERING (ICCKE 2019), 2019, : 351 - 355
  • [30] Late fusion for acoustic scene classification using swarm intelligence
    Ding, Biyun
    Zhang, Tao
    Liu, Ganjun
    Kong, Lingguo
    Geng, Yanzhang
    APPLIED ACOUSTICS, 2022, 192