{"total":28,"rows":[{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2508.04665","title":"Perch 2.0: The Bittern Lesson for Bioacoustics","created":"2025-08-06","cited_by_count":26,"area":null},{"id":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","cited_by_count":14,"area":null},{"id":"2211.13189","title":"ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification","created":"2022-11-23","cited_by_count":13,"area":null},{"id":"2406.14686","title":"A Contrastive Learning Approach to Mitigate Bias in Speech Models","created":"2024-06-20","cited_by_count":9,"area":null},{"id":"2302.12712","title":"Amortised Invariance Learning for Contrastive Self-Supervision","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2110.00046","title":"SpliceOut: A Simple and Efficient Audio Augmentation Method","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2401.05064","title":"Singer Identity Representation Learning using Self-Supervised Techniques","created":"2024-01-10","cited_by_count":6,"area":null},{"id":"2207.04471","title":"Towards Proper Contrastive Self-supervised Learning Strategies For Music Audio Representation","created":"2022-07-10","cited_by_count":5,"area":null},{"id":"2209.14345","title":"Audio Barlow Twins: Self-Supervised Audio Representation Learning","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2204.04170","title":"Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning","created":"2022-04-08","cited_by_count":4,"area":null},{"id":"2305.17191","title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2406.15862","title":"Speech Analysis of Language Varieties in Italy","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2207.12121","title":"Cross-Modal Contrastive Representation Learning for Audio-to-Image Generation","created":"2022-07-20","cited_by_count":2,"area":null},{"id":"2309.05843","title":"Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2409.09647","title":"Self-supervised Learning for Acoustic Few-Shot Classification","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2308.07221","title":"AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2510.10862","title":"A Joint Learning Approach to Hardware Caching and Prefetching","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.20602","title":"Resounding Acoustic Fields with Reciprocity","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2110.07082","title":"The Impact of Spatiotemporal Augmentations on Self-Supervised Audiovisual Representation Learning","created":"2021-10-13","cited_by_count":0,"area":null},{"id":"2111.03971","title":"Towards noise robust trigger-word detection with contrastive learning pre-task for fast on-boarding of new trigger-words","created":"2021-11-06","cited_by_count":0,"area":null},{"id":"2309.11895","title":"Audio Contrastive-based Fine-tuning: Decoupling Representation Learning and Classification","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2510.10719","title":"SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation","created":"2025-10-12","cited_by_count":0,"area":null},{"id":"2605.26523","title":"StreamSplit: Continuous Audio Representation Learning via Uncertainty-Guided Adaptive Splitting","created":"2026-05-26","cited_by_count":0,"area":null}],"next_cursor":null}