mlsanityData to 7 Oct 2026

Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data

arXiv 2202.00097 ↗First posted 31 Jan 2022cs.LG cs.SDcited by 8

Not on the map. Why?

Abstract (arXiv)

Large scale databases with high-quality manual annotations are scarce in audio domain. We thus explore a self-supervised graph approach to learning audio representations from highly limited labelled data. Considering each audio sample as a graph node, we propose a subgraph-based framework with novel self-supervision tasks that can learn effective audio representations. During training, subgraphs are constructed by sampling the entire pool of available training data to exploit the relationship between the labelled and unlabeled audio samples. During inference, we use random edges to alleviate the overhead of graph construction. We evaluate our model on three benchmark audio databases, and two tasks: acoustic event detection and speech emotion recognition. Our semi-supervised model performs better or on par with fully supervised models and outperforms several competitive existing models. Our model is compact (240k parameters), and can produce generalized audio representations that are robust to different types of signal noise.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 44 of its 67 references that are in the map. First posted on arXiv 31 Jan 2022.

Builds on

44 of 67 references.

References · 44

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Graph Attention Networkscited by 8,854
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  6. 2017Inductive Representation Learning on Large Graphscited by 6,284
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  9. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  10. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  11. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  12. 2016CNN Architectures for Large-Scale Audio Classificationcited by 701
32 more
  1. 2020Benchmarking Graph Neural Networkscited by 672
  2. 2021SUPERB: Speech processing Universal PERformance Benchmarkcited by 652
  3. 2021AST: Audio Spectrogram Transformercited by 634
  4. 2019GraphSAINT: Graph Sampling Based Inductive Learning Methodcited by 618
  5. 2019PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognitioncited by 563
  6. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 544
  7. 2021VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Textcited by 427
  8. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 166
  9. 2020When Does Self-Supervision Help Graph Convolutional Networks?cited by 121
  10. 2020Self-supervised Learning on Graphs: Deep Insights and New Directioncited by 108
  11. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  12. 2021BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representationcited by 106
  13. 2020Graph Meta Learning via Local Subgraphscited by 89
  14. 2019Learning Problem-agnostic Speech Representations from Multiple Self-supervised Taskscited by 87
  15. 2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
  16. 2020Subgraph Neural Networkscited by 73
  17. 2016Very Deep Convolutional Neural Networks for Raw Waveformscited by 68
  18. 2021Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognitioncited by 68
  19. 2020Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networkscited by 54
  20. 2020Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learningcited by 33
  21. 2020Disentangled Speech Embeddings using Cross-modal Self-supervisioncited by 30
  22. 2020Self-supervised Training of Graph Convolutional Networkscited by 24
  23. 2021SERAB: A multi-lingual benchmark for speech emotion recognitioncited by 22
  24. 2020Semi-supervised Multi-modal Emotion Recognition with Cross-Modal Distribution Matchingcited by 13
  25. 2020Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?cited by 9
  26. 2020Compact Graph Architecture for Speech Emotion Recognitioncited by 9
  27. 2020An Ontology-Aware Framework for Audio Event Classificationcited by 5
  28. 2021Multi-Channel Speech Enhancement using Graph Neural Networkscited by 5
  29. 2018SGR: Self-Supervised Spectral Graph Representation Learningcited by 3
  30. 2020Advancing Multiple Instance Learning with Attention Modeling for Categorical Speech Emotion Recognitioncited by 3
  31. 2019Secost: Sequential co-supervision for large scale weakly labeled audio event detectioncited by 1
  32. 2021Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognitioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 0; 2026: 3.

8 papers.

  1. 2023TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classificationcited by 9
  2. 2023Can Self-Supervised Representation Learning Methods Withstand Distribution Shifts and Corruptions?cited by 5
  3. 2022Visually-aware Acoustic Event Detection using Heterogeneous Graphscited by 4
  4. 2023Heterogeneous Graph Learning for Acoustic Event Classificationcited by 2
  5. 2024Graph in Graph Neural Networkcited by 0
  6. 2026Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion Recognitioncited by 0
  7. 2026Low resource cross-modal alignment using HGNN to enhance speech representationcited by 0
  8. 2026Enhancing speech representation learning with cross-modal knowledge transfer with HGNN under low resource settings: the case study of Yembacited by 0