mlsanityData to 7 Oct 2026

AudRandAug: Random Image Augmentations for Audio Classification

arXiv 2309.04762 ↗First posted 9 Sep 2023cs.SD cs.AI cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Data augmentation has proven to be effective in training neural networks. Recently, a method called RandAug was proposed, randomly selecting data augmentation techniques from a predefined search space. RandAug has demonstrated significant performance improvements for image-related tasks while imposing minimal computational overhead. However, no prior research has explored the application of RandAug specifically for audio data augmentation, which converts audio into an image-like pattern. To address this gap, we introduce AudRandAug, an adaptation of RandAug for audio data. AudRandAug selects data augmentation policies from a dedicated audio search space. To evaluate the effectiveness of AudRandAug, we conducted experiments using various models and datasets. Our findings indicate that AudRandAug outperforms other existing data augmentation methods regarding accuracy performance.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 62 references that are in the map. First posted on arXiv 9 Sep 2023.

Builds on

25 of 62 references.

References · 25

  1. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  2. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  3. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
  4. 2016SoundNet: Learning Sound Representations from Unlabeled Videocited by 244
  5. 2018A Hierarchical Latent Vector Model for Learning Long-Term Structure in Musiccited by 131
  6. 2016Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classificationcited by 84
  7. 2020Natural Language Processing Advancements By Deep Learning: A Surveycited by 50
  8. 2016Convolutional Recurrent Neural Networks for Music Classificationcited by 49
  9. 2020Rethinking CNN Models for Audio Classificationcited by 48
  10. 2019Data augmentation approaches for improving animal audio classificationcited by 31
  11. 2020ESResNet: Environmental Sound Classification Based on Visual Domain Modelscited by 31
  12. 2021SpecMix : A Mixed Sample Data Augmentation method for Training withTime-Frequency Domain Featurescited by 30
13 more
  1. 2017Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveformscited by 27
  2. 2023Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Modelscited by 21
  3. 2017Raw Waveform-based Audio Classification Using Sample-level CNN Architecturescited by 12
  4. 2022Investigating Multi-Feature Selection and Ensembling for Audio Classificationcited by 9
  5. 2018Convolutional Neural Network Achieves Human-level Accuracy in Music Genre Classificationcited by 7
  6. 2021SpliceOut: A Simple and Efficient Audio Augmentation Methodcited by 7
  7. 2022Precise Single-stage Detectorcited by 7
  8. 2019Multi-stream Network With Temporal Attention For Environmental Sound Classificationcited by 6
  9. 2022Random Data Augmentation based Enhancement: A Generalized Enhancement Approach for Medical Datasetscited by 6
  10. 2023Understanding EEG signals for subject-wise Definition of Armoni Activitiescited by 6
  11. 2022Data Dimension Reduction makes ML Algorithms efficientcited by 2
  12. 2022Advanced Audio Aid for Blind Peoplecited by 2
  13. 2023Go Together: Bridging the Gap between Learners and Teacherscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024OxML Challenge 2023: Carcinoma classification using data augmentationcited by 1
  2. 2024FaceSaliencyAug: Mitigating Geographic, Gender and Stereotypical Biases via Saliency-Based Data Augmentationcited by 0
  3. 2024Saliency-Based diversity and fairness Metric and FaceKeepOriginalAugment: A Novel Approach for Enhancing Fairness and Diversitycited by 0