{"total":25,"rows":[{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2102.07810","title":"HDMI: High-order Deep Multiplex Infomax","created":"2021-02-15","cited_by_count":82,"area":null},{"id":"2111.10367","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","created":"2021-11-19","cited_by_count":72,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2106.10132","title":"VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion","created":"2021-06-18","cited_by_count":64,"area":null},{"id":"2205.02444","title":"Cross-modal Contrastive Learning for Speech Translation","created":"2022-05-05","cited_by_count":61,"area":null},{"id":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44,"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":"2107.06898","title":"Towards quantifying information flows: relative entropy in deep neural networks and the renormalization group","created":"2021-07-14","cited_by_count":14,"area":null},{"id":"2107.06456","title":"AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defense","created":"2021-07-14","cited_by_count":10,"area":null},{"id":"2102.08015","title":"Improving speech recognition models with small samples for air traffic control systems","created":"2021-02-16","cited_by_count":6,"area":null},{"id":"2106.13085","title":"Coherent, super resolved radar beamforming using self-supervised learning","created":"2021-06-21","cited_by_count":4,"area":null},{"id":"2108.12229","title":"ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection","created":"2021-08-27","cited_by_count":4,"area":null},{"id":"2406.02285","title":"Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2103.01461","title":"Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect","created":"2021-03-02","cited_by_count":2,"area":null},{"id":"2110.13653","title":"Learning Speaker Representation with Semi-supervised Learning approach for Speaker Profiling","created":"2021-10-24","cited_by_count":2,"area":null},{"id":"2104.02571","title":"Speaker embeddings by modeling channel-wise correlations","created":"2021-04-06","cited_by_count":1,"area":null},{"id":"2111.01276","title":"Multi network InfoMax: A pre-training method involving graph convolutional networks","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2112.08929","title":"Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification","created":"2021-12-16","cited_by_count":1,"area":null},{"id":"2206.09058","title":"NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling","created":"2022-06-18","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":"2408.13341","title":"Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples","created":"2024-08-23","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":"2606.05561","title":"InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization","created":"2026-06-04","cited_by_count":0,"area":null}],"next_cursor":null}