mlsanityData to 14 Oct 2026

RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification

arXiv 2405.02996 ↗First posted 5 May 2024cs.SD cs.AI eess.AScited by 12

Not on the map. Why?

Abstract (arXiv)

Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored pretrained speech models, which, as human-originated sounds, intuitively would share closer resemblance to lung sounds. This paper explores the efficacy of pretrained speech models for respiratory sound classification. We find that there is a characterization gap between speech and lung sound samples, and to bridge this gap, data augmentation is essential. However, the most widely used augmentation technique for audio and speech, SpecAugment, requires 2-dimensional spectrogram format and cannot be applied to models pretrained on speech waveforms. To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models. Experimental results show that our approach outperforms the SpecAugment, demonstrating a substantial improvement in the accuracy of minority disease classes, reaching up to 7.14%.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 26 of its 35 references that are in the map. First posted on arXiv 5 May 2024.

Builds on

26 of 35 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2016Layer Normalizationcited by 5,669
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  6. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  7. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  8. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  9. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 666
  10. 2021AST: Audio Spectrogram Transformercited by 643
  11. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  12. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 574
14 more
  1. 2021Domain Generalization with MixStylecited by 566
  2. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 476
  3. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 467
  4. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  5. 2020Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspectivecited by 120
  6. 2015Dropout as data augmentationcited by 27
  7. 2020RespireNet: A Deep Neural Network for Accurately Detecting Abnormal Lung Sounds in Limited Data Settingcited by 26
  8. 2023Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classificationcited by 24
  9. 2021Prototype Learning for Interpretable Respiratory Sound Analysiscited by 21
  10. 2023Stethoscope-guided Supervised Contrastive Learning for Cross-domain Adaptation on Respiratory Sound Classificationcited by 16
  11. 2022Pretraining Respiratory Sound Representations using Metadata and Contrastive Learningcited by 15
  12. 2022Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysiscited by 13
  13. 2023Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalancecited by 11
  14. 2018End-to-End Speech Recognition From the Raw Waveformcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 6.

12 papers.

  1. 2024BTS: Bridging Text and Sound Modalities for Metadata-Aided Respiratory Sound Classificationcited by 12
  2. 2025Tri-MTL: A Triple Multitask Learning Approach for Respiratory Disease Diagnosiscited by 3
  3. 2025Improving Respiratory Sound Classification with Architecture-Agnostic Knowledge Distillation from Ensemblescited by 3
  4. 2024Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classificationcited by 2
  5. 2026Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventionscited by 1
  6. 2025Noise-Agnostic Multitask Whisper Training for Reducing False Alarm Errors in Call-for-Help Detectioncited by 0
  7. 2025Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformerscited by 0
  8. 2026PC-MCL: Patient-Consistent Multi-Cycle Learning with multi-label bias correction for respiratory sound classificationcited by 0
  9. 2026Resp-Agent: An Agent-Based System for Multimodal Respiratory Sound Generation and Disease Diagnosiscited by 0
  10. 2026Meta-Ensemble Learning with Diverse Data Splits for Improved Respiratory Sound Classificationcited by 0
  11. 2026Quality Adaptive Angular Margin Learning for Respiratory Sound Classificationcited by 0
  12. 2026Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classificationcited by 0