mlsanityData to 7 Oct 2026

Asca: less audio data is more insightful

arXiv 2309.13373 ↗First posted 23 Sep 2023cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Audio recognition in specialized areas such as birdsong and submarine acoustics faces challenges in large-scale pre-training due to the limitations in available samples imposed by sampling environments and specificity requirements. While the Transformer model excels in audio recognition, its dependence on vast amounts of data becomes restrictive in resource-limited settings. Addressing this, we introduce the Audio Spectrogram Convolution Attention (ASCA) based on CoAtNet, integrating a Transformer-convolution hybrid architecture, novel network design, and attention techniques, further augmented with data enhancement and regularization strategies. On the BirdCLEF2023 and AudioSet(Balanced), ASCA achieved accuracies of 81.2% and 35.1%, respectively, significantly outperforming competing methods. The unique structure of our model enriches output, enabling generalization across various audio detection tasks. Our code can be found at https://github.com/LeeCiang/ASCA.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 36 references that are in the map. First posted on arXiv 23 Sep 2023.

Builds on

23 of 36 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  7. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  8. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  9. 2018Self-Attention with Relative Position Representationscited by 1,112
  10. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  11. 2020VGGSound: A Large-scale Audio-Visual Datasetcited by 641
  12. 2021AST: Audio Spectrogram Transformercited by 634
11 more
  1. 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
  2. 2021AudioCLIP: Extending CLIP to Image, Text and Audiocited by 335
  3. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  4. 2021Vision Transformer for Small-Size Datasetscited by 122
  5. 2016Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classificationcited by 84
  6. 2021PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregationcited by 81
  7. 2017Learning from Between-class Examples for Deep Sound Recognitioncited by 53
  8. 2016Convolutional Recurrent Neural Networks for Music Classificationcited by 49
  9. 2022How to Train Vision Transformer on Small-scale Datasets?cited by 34
  10. 2019Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimizationcited by 29
  11. 2023Multiscale Audio Spectrogram Transformer for Efficient Audio Classificationcited by 16

Built on by

Not cited yet.