mlsanityData to 7 Oct 2026

Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices

arXiv 2203.12314 ↗First posted 23 Mar 2022cs.SD cs.LG eess.AScited by 7

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a robust and low complexity system for Acoustic Scene Classification (ASC), the task of identifying the scene of an audio recording. We first construct an ASC baseline system in which a novel inception-residual-based network architecture is proposed to deal with the mismatched recording device issue. To further improve the performance but still satisfy the low complexity model, we apply two techniques: ensemble of multiple spectrograms and channel reduction on the ASC baseline system. By conducting extensive experiments on the benchmark DCASE 2020 Task 1A Development dataset, we achieve the best model performing an accuracy of 69.9% and a low complexity of 2.4M trainable parameters, which is competitive to the state-of-the-art ASC systems and potential for real-life applications on edge devices.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 23 Mar 2022.

Builds on

17 of 36 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
  5. 2015Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applicationscited by 161
  6. 2018Data Augmentation using Random Image Cropping and Patching for Deep CNNscited by 87
  7. 2017Learning from Between-class Examples for Deep Sound Recognitioncited by 53
  8. 2020Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutionscited by 48
  9. 2018Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Networkcited by 16
  10. 2018SubSpectralNet - Using Sub-Spectrogram based Convolutional Neural Networks for Acoustic Scene Classificationcited by 10
  11. 2020Robust Acoustic Scene Classification using a Multi-Spectrogram Encoder-Decoder Frameworkcited by 8
  12. 2021Multi-view Audio and Music Classificationcited by 8
5 more
  1. 2019Acoustic Scene Classification by Implicitly Identifying Distinct Sound Eventscited by 6
  2. 2020Sound Context Classification Basing on Join Learning Model and Multi-Spectrogram Featurescited by 5
  3. 2021An Audio-Visual Dataset and Deep Learning Frameworks for Crowded Scene Classificationcited by 5
  4. 2020Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Dampingcited by 3
  5. 2021Robust Deep Learning Frameworks for Acoustic Scene and Respiratory Sound Classificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 2; 2025: 0; 2026: 1.

7 papers.

  1. 2024Deepfake Audio Detection Using Spectrogram-based Feature and Ensemble of Deep Learning Modelscited by 5
  2. 2023An Inception-Residual-Based Architecture with Multi-Objective Loss for Detecting Respiratory Anomaliescited by 2
  3. 2022Low-complexity deep learning frameworks for acoustic scene classificationcited by 1
  4. 2022DCASE 2022: Comparative Analysis Of CNNs For Acoustic Scene Classification Under Low-Complexity Considerationscited by 0
  5. 2023Low-complexity deep learning frameworks for acoustic scene classification using teacher-student scheme and multiple spectrogramscited by 0
  6. 2024A Toolchain for Comprehensive Audio/Video Analysis Using Deep Learning Based Multimodal Approach (A use case of riot or violent context detection)cited by 0
  7. 2026Environmental Sound Deepfake Detection Using Deep-Learning Frameworkcited by 0