mlsanityData to 14 Oct 2026

Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning

arXiv 2010.13991 ↗First posted 27 Oct 2020cs.CLcited by 34

Not on the map. Why?

Abstract (arXiv)

Self-supervised visual pretraining has shown significant progress recently. Among those methods, SimCLR greatly advanced the state of the art in self-supervised and semi-supervised learning on ImageNet. The input feature representations for speech and visual tasks are both continuous, so it is natural to consider applying similar objective on speech representation learning. In this paper, we propose Speech SimCLR, a new self-supervised objective for speech representation learning. During training, Speech SimCLR applies augmentation on raw speech and its spectrogram. Its objective is the combination of contrastive loss that maximizes agreement between differently augmented samples in the latent space and reconstruction loss of input representation. The proposed method achieved competitive results on speech emotion recognition and speech recognition.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 11; 2023: 4; 2024: 4; 2025: 3; 2026: 3.

34 papers.

Sort:

By area:

  1. 2022Self-Supervised Speech Representation Learning: A Reviewcited by 260
  2. 2021SSAST: Self-Supervised Audio Spectrogram Transformercited by 169
  3. 2021DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERTcited by 144
  4. 2021PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognitioncited by 53
  5. 2021Injecting Text in Self-Supervised Speech Pretrainingcited by 24
  6. 2022Sound Localization by Self-Supervised Time Delay Estimationcited by 18
  7. 2024CR-CTC: Consistency regularization on CTC for improved speech recognitioncited by 17
  8. 2021Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classificationcited by 16
  9. 2022That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulationcited by 12
  10. 2024SpeechPrompt: Prompting Speech Language Models for Speech Processing Taskscited by 12
  11. 2022CCC-wav2vec 2.0: Clustering aided Cross Contrastive Self-supervised learning of speech representationscited by 11
  12. 2022Equivariant Self-Supervision for Musical Tempo Estimationcited by 9
22 more
  1. 2022Self-supervised Graphs for Audio Representation Learning with Limited Labeled Datacited by 8
  2. 2022SampleMatch: Drum Sample Retrieval by Musical Contextcited by 8
  3. 2021Pretext Tasks selection for multitask self-supervised speech representation learningcited by 7
  4. 2023Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysiscited by 6
  5. 2022data2vec-aqc: Search for the right Teaching Assistant in the Teacher-Student training setupcited by 5
  6. 2021Computer Vision Self-supervised Learning Methods on Time Seriescited by 4
  7. 2021Conditional independence for pretext task selection in Self-supervised speech representation learningcited by 3
  8. 2024ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Taskscited by 3
  9. 2025Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentationcited by 3
  10. 2022Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognitioncited by 2
  11. 2022Contrastive Siamese Network for Semi-supervised Speech Recognitioncited by 2
  12. 2023Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domainscited by 2
  13. 2023Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signalscited by 2
  14. 2021Multi-Variant Consistency based Self-supervised Learning for Robust Automatic Speech Recognitioncited by 1
  15. 2022TriNet: stabilizing self-supervised learning from complete or slow collapse on ASRcited by 1
  16. 2023MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognitioncited by 1
  17. 2024Removing Speaker Information from Speech Representation using Variable-Length Soft Poolingcited by 1
  18. 2025DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Modelcited by 1
  19. 2026SITA: Learning Speaker-Invariant and Tone-Aware Speech Representations for Low-Resource Tonal Languagescited by 1
  20. 2025Latent Space Consistency for Sparse-View CT Reconstructioncited by 0
  21. 2026DASH: Dual-View Self-Distillation with Multi-Layer Hidden Representations for Robust Speech Recognitioncited by 0
  22. 2026Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptionscited by 0