{"total":51,"rows":[{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2306.00107","title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","created":"2023-05-31","cited_by_count":181,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"id":"2210.14648","title":"Masked Modeling Duo: Learning Representations by Encouraging Both Networks to Model the Input","created":"2022-10-26","cited_by_count":23,"area":null},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2210.15386","title":"Opening the Black Box of wav2vec Feature Encoder","created":"2022-10-27","cited_by_count":18,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2403.02522","title":"HeAR -- Health Acoustic Representations","created":"2024-03-04","cited_by_count":15,"area":null},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"area":null},{"id":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2209.01478","title":"Equivariant Self-Supervision for Musical Tempo Estimation","created":"2022-09-03","cited_by_count":9,"area":null},{"id":"2309.07391","title":"EnCodecMAE: Leveraging neural codecs for universal audio representation learning","created":"2023-09-14","cited_by_count":9,"area":null},{"id":"2602.07143","title":"Massive Sound Embedding Benchmark (MSEB)","created":"2026-02-06","cited_by_count":9,"area":null},{"id":"2408.02514","title":"Stem-JEPA: A Joint-Embedding Predictive Architecture for Musical Stem Compatibility Estimation","created":"2024-08-05","cited_by_count":8,"area":null},{"id":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"area":null},{"id":"2307.05161","title":"On the Effectiveness of Speech Self-supervised Learning for Music","created":"2023-07-11","cited_by_count":5,"area":null},{"id":"2211.01519","title":"SLICER: Learning universal audio representations using low-resource self-supervised pre-training","created":"2022-11-02","cited_by_count":4,"area":null},{"id":"2305.01578","title":"Self-supervised learning for infant cry analysis","created":"2023-05-02","cited_by_count":4,"area":null},{"id":"2401.08889","title":"On the Effect of Data-Augmentation on Local Embedding Properties in the Contrastive Learning of Music Audio Representations","created":"2024-01-17","cited_by_count":4,"area":null},{"id":"2404.09177","title":"An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"2407.18058","title":"I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2211.01515","title":"MAST: Multiscale Audio Spectrogram Transformers","created":"2022-11-02","cited_by_count":3,"area":null},{"id":"2304.05600","title":"Looking Similar, Sounding Different: Leveraging Counterfactual Cross-Modal Pairs for Audiovisual Representation Learning","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2308.07121","title":"Active Bird2Vec: Towards End-to-End Bird Sound Monitoring with Transformers","created":"2023-08-14","cited_by_count":3,"area":null},{"id":"2502.12511","title":"Myna: Masking-Based Contrastive Learning of Musical Representations","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2204.03421","title":"Self-supervised learning for robust voice cloning","created":"2022-04-07","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":"2311.07534","title":"Unsupervised Musical Object Discovery from Audio","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2402.02889","title":"Exploring Federated Self-Supervised Learning for General Purpose Audio Understanding","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2506.23873","title":"Emergent musical properties of a transformer under contrastive self-supervised learning","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2203.10425","title":"A Study on Robustness to Perturbations for Representations of Environmental Sound","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2203.15519","title":"Learning neural audio features without supervision","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2206.00893","title":"Leveraging Systematic Knowledge of 2D Transformations","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2307.01212","title":"Of Spiky SVDs and Music Recommendation","created":"2023-06-30","cited_by_count":1,"area":null},{"id":"2312.14005","title":"On the choice of the optimal temporal support for audio classification with Pre-trained embeddings","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2502.06664","title":"Evaluation of Deep Audio Representations for Hearables","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2208.09096","title":"Representation Learning for the Automatic Indexing of Sound Effects Libraries","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2209.02388","title":"Pathway to Future Symbiotic Creativity","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2211.05304","title":"Contrastive Self-Supervised Learning for Skeleton Representations","created":"2022-11-10","cited_by_count":0,"area":null},{"id":"2303.05668","title":"UNFUSED: UNsupervised Finetuning Using SElf supervised Distillation","created":"2023-03-10","cited_by_count":0,"area":"distill"},{"id":"2307.07265","title":"AudioInceptionNeXt: TCL AI LAB Submission to EPIC-SOUND Audio-Based-Interaction-Recognition Challenge 2023","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2608.16203","title":"INSPIRE: A Benchmark for Instruction-Aware Speech Retrieval","created":"2026-08-17","cited_by_count":0,"area":null}],"next_cursor":null}