{"total":39,"rows":[{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"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":"2201.04309","title":"Robust Contrastive Learning against Noisy Views","created":"2022-01-12","cited_by_count":45,"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":"2110.07313","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","created":"2021-10-14","cited_by_count":22,"area":null},{"id":"2107.00249","title":"OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation","created":"2021-07-01","cited_by_count":20,"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":"2406.05629","title":"Separating the \"Chirp\" from the \"Chat\": Self-supervised Visual Grounding of Sound and Language","created":"2024-06-09","cited_by_count":17,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14,"area":null},{"id":"2306.00349","title":"CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2110.13623","title":"Contrastive Neural Processes for Self-Supervised Learning","created":"2021-10-24","cited_by_count":9,"area":null},{"id":"2208.01141","title":"SampleMatch: Drum Sample Retrieval by Musical Context","created":"2022-08-01","cited_by_count":8,"area":null},{"id":"2212.08649","title":"Better May Not Be Fairer: A Study on Subgroup Discrepancy in Image Classification","created":"2022-12-16","cited_by_count":7,"area":null},{"id":"2304.10309","title":"Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2409.11264","title":"LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Tagging","created":"2024-09-17","cited_by_count":7,"area":null},{"id":"2105.02132","title":"Self-Supervised Learning from Automatically Separated Sound Scenes","created":"2021-05-05","cited_by_count":6,"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":"2304.14019","title":"XAI-based Comparison of Input Representations for Audio Event Classification","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2309.00878","title":"Pretraining Representations for Bioacoustic Few-shot Detection using Supervised Contrastive Learning","created":"2023-09-02","cited_by_count":2,"area":null},{"id":"2309.15938","title":"Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation","created":"2023-09-27","cited_by_count":2,"area":null},{"id":"2312.02205","title":"Disentangling the Effects of Data Augmentation and Format Transform in Self-Supervised Learning of Image Representations","created":"2023-12-02","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2412.11449","title":"Whisper-GPT -- Continuous Discrete Hybrid Representation Language Models For Speech And Music","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2110.03183","title":"Attention is All You Need? Good Embeddings with Statistics are enough:Large Scale Audio Understanding without Transformers/ Convolutions/ BERTs/ Mixers/ Attention/ RNNs or ....","created":"2021-10-07","cited_by_count":1,"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":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","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":"2111.13321","title":"Learning source-aware representations of music in a discrete latent space","created":"2021-11-26","cited_by_count":0,"area":null},{"id":"2201.01771","title":"Self-Supervised Beat Tracking in Musical Signals with Polyphonic Contrastive Learning","created":"2022-01-05","cited_by_count":0,"area":null},{"id":"2202.13673","title":"Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2203.08490","title":"Learning Audio Representations with MLPs","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2204.11479","title":"End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2210.15750","title":"One-Shot Acoustic Matching Of Audio Signals -- Learning to Hear Music In Any Room/ Concert Hall","created":"2022-10-27","cited_by_count":0,"area":null},{"id":"2303.10446","title":"Content Adaptive Front End For Audio Classification","created":"2023-03-18","cited_by_count":0,"area":null},{"id":"2309.08751","title":"Diverse Audio Embeddings -- Bringing Features Back Outperforms CLAP!","created":"2023-09-15","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":"2510.22655","title":"Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections","created":"2025-10-26","cited_by_count":0,"area":null}],"next_cursor":null}