mlsanityData to 7 Oct 2026

TC-SKNet with GridMask for Low-complexity Classification of Acoustic scene

arXiv 2210.02287 ↗First posted 5 Oct 2022cs.SD cs.LG eess.AScited by 12

Not on the map. Why?

Abstract (arXiv)

Convolution neural networks (CNNs) have good performance in low-complexity classification tasks such as acoustic scene classifications (ASCs). However, there are few studies on the relationship between the length of target speech and the size of the convolution kernels. In this paper, we combine Selective Kernel Network with Temporal-Convolution (TC-SKNet) to adjust the receptive field of convolution kernels to solve the problem of variable length of target voice while keeping low-complexity. GridMask is a data augmentation strategy by masking part of the raw data or feature area. It can enhance the generalization of the model as the role of dropout. In our experiments, the performance gain brought by GridMask is stronger than spectrum augmentation in ASCs. Finally, we adopt AutoML to search best structure of TC-SKNet and hyperparameters of GridMask for improving the classification performance. As a result, a peak accuracy of 59.87% TC-SKNet is equivalent to that of SOTA, but the parameters only use 20.9 K.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 14 of its 23 references that are in the map. First posted on arXiv 5 Oct 2022.

Builds on

14 of 23 references.

References · 14

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2013Network In Networkcited by 600
  6. 2019Selective Kernel Networkscited by 401
  7. 2020GridMask Data Augmentationcited by 123
  8. 2019Temporal Convolution for Real-time Keyword Spotting on Mobile Devicescited by 48
  9. 2020Acoustic scene classification in DCASE 2020 Challenge: generalization across devices and low complexity solutionscited by 48
  10. 2020Accurate Detection of Wake Word Start and End Using a CNNcited by 24
  11. 2020Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentationcited by 13
  12. 2020ASAPP-ASR: Multistream CNN and Self-Attentive SRU for SOTA Speech Recognitioncited by 10
2 more
  1. 2019Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimizationcited by 9
  2. 2018Fast ASR-free and almost zero-resource keyword spotting using DTW and CNNs for humanitarian monitoringcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 7; 2025: 1.

12 papers.

  1. 2024MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysiscited by 14
  2. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  3. 2023Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adaptercited by 0
  4. 2023GMTR: Graph Matching Transformerscited by 0
  5. 2023DarkShot: Lighting Dark Images with Low-Compute and High-Qualitycited by 0
  6. 2024TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processingcited by 0
  7. 2024TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networkscited by 0
  8. 2024T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Imagecited by 0
  9. 2024Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithmscited by 0
  10. 2024Towards General Deepfake Detection with Dynamic Curriculumcited by 0
  11. 2024Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphscited by 0
  12. 2025Mask6D: Masked Pose Priors For 6D Object Pose Estimationcited by 0