{"total":97,"rows":[{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"area":null},{"id":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130,"area":null},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78,"area":null},{"id":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2401.03497","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","created":"2024-01-07","cited_by_count":53,"area":null},{"id":"2409.07402","title":"What to align in multimodal contrastive learning?","created":"2024-09-11","cited_by_count":47,"area":null},{"id":"2205.06226","title":"The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning","created":"2022-05-12","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":"2310.16917","title":"MimicTouch: Leveraging Multi-modal Human Tactile Demonstrations for Contact-rich Manipulation","created":"2023-10-25","cited_by_count":34,"area":null},{"id":"2208.12208","title":"Contrastive Audio-Language Learning for Music","created":"2022-08-25","cited_by_count":33,"area":null},{"id":"2308.14395","title":"UMMAFormer: A Universal Multimodal-adaptive Transformer Framework for Temporal Forgery Localization","created":"2023-08-28","cited_by_count":33,"area":null},{"id":"2310.15247","title":"SyncFusion: Multimodal Onset-synchronized Video-to-Audio Foley Synthesis","created":"2023-10-23","cited_by_count":24,"area":null},{"id":"2406.16148","title":"Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking","created":"2024-06-23","cited_by_count":23,"area":null},{"id":"2110.03414","title":"SERAB: A multi-lingual benchmark for speech emotion recognition","created":"2021-10-07","cited_by_count":22,"area":null},{"id":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","cited_by_count":19,"area":null},{"id":"2405.08576","title":"Hearing Touch: Audio-Visual Pretraining for Contact-Rich Manipulation","created":"2024-05-14","cited_by_count":14,"area":null},{"id":"2406.01253","title":"animal2vec and MeerKAT: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics","created":"2024-06-03","cited_by_count":14,"area":null},{"id":"2410.05016","title":"T-JEPA: Augmentation-Free Self-Supervised Learning for Tabular Data","created":"2024-10-07","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":"2408.16221","title":"SSDM: Scalable Speech Dysfluency Modeling","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2210.01116","title":"That Sounds Right: Auditory Self-Supervision for Dynamic Robot Manipulation","created":"2022-10-03","cited_by_count":12,"area":null},{"id":"2104.12922","title":"One Billion Audio Sounds from GPU-enabled Modular Synthesis","created":"2021-04-27","cited_by_count":11,"area":null},{"id":"2306.00561","title":"Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners","created":"2023-06-01","cited_by_count":11,"area":null},{"id":"2203.09129","title":"Contrastive Learning with Positive-Negative Frame Mask for Music Representation","created":"2022-03-17","cited_by_count":10,"area":null},{"id":"2206.12038","title":"BYOL-S: Learning Self-supervised Speech Representations by Bootstrapping","created":"2022-06-24","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":"2401.04210","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","created":"2024-01-08","cited_by_count":9,"area":null},{"id":"2111.05329","title":"Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity","created":"2021-11-09","cited_by_count":8,"area":null},{"id":"2202.00097","title":"Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data","created":"2022-01-31","cited_by_count":8,"area":null},{"id":"2205.07390","title":"Learning Representations for New Sound Classes With Continual Self-Supervised Learning","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2208.01141","title":"SampleMatch: Drum Sample Retrieval by Musical Context","created":"2022-08-01","cited_by_count":8,"area":null},{"id":"2312.09578","title":"Self-Supervised Learning for Anomalous Sound Detection","created":"2023-12-15","cited_by_count":8,"area":null},{"id":"2507.16596","title":"A Multimodal Deviation Perceiving Framework for Weakly-Supervised Temporal Forgery Localization","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2110.08895","title":"DECAR: Deep Clustering for learning general-purpose Audio Representations","created":"2021-10-17","cited_by_count":7,"area":null},{"id":"2210.07978","title":"Improving generalizability of distilled self-supervised speech processing models under distorted settings","created":"2022-10-14","cited_by_count":7,"area":null},{"id":"2506.18843","title":"USAD: Universal Speech and Audio Representation via Distillation","created":"2025-06-23","cited_by_count":7,"area":null},{"id":"2202.05583","title":"Similarity learning for wells based on logging data","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2203.16637","title":"Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load","created":"2022-03-30","cited_by_count":6,"area":null},{"id":"2212.08663","title":"Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning","created":"2022-12-19","cited_by_count":6,"area":null},{"id":"2407.03836","title":"ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2205.06887","title":"AVCAffe: A Large Scale Audio-Visual Dataset of Cognitive Load and Affect for Remote Work","created":"2022-05-13","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":"2412.15023","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2109.00783","title":"Computer Vision Self-supervised Learning Methods on Time Series","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2206.07041","title":"Learning Behavior Representations Through Multi-Timescale Bootstrapping","created":"2022-06-14","cited_by_count":4,"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":"2303.08811","title":"Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis","created":"2023-03-15","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":"2407.16417","title":"On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis","created":"2024-07-23","cited_by_count":4,"area":null},{"id":"2508.14130","title":"EmoSLLM: Parameter-Efficient Adaptation of LLMs for Speech Emotion Recognition","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2207.06767","title":"Semi-supervised cross-lingual speech emotion recognition","created":"2022-07-14","cited_by_count":3,"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":"2304.11472","title":"A Comparative Study of Pre-trained Speech and Audio Embeddings for Speech Emotion Recognition","created":"2023-04-22","cited_by_count":3,"area":null},{"id":"2305.12712","title":"LEAN: Light and Efficient Audio Classification Network","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2309.09690","title":"Do learned speech symbols follow Zipf's law?","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2410.02387","title":"BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization","created":"2024-10-03","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":"2207.14760","title":"SimCURL: Simple Contrastive User Representation Learning from Command Sequences","created":"2022-07-29","cited_by_count":2,"area":null},{"id":"2211.06646","title":"Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings","created":"2022-11-12","cited_by_count":2,"area":null},{"id":"2308.11923","title":"Audio Difference Captioning Utilizing Similarity-Discrepancy Disentanglement","created":"2023-08-23","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":"2309.15938","title":"Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation","created":"2023-09-27","cited_by_count":2,"area":null},{"id":"2406.06341","title":"Predicting Heart Activity from Speech using Data-driven and Knowledge-based features","created":"2024-06-10","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":"2506.02059","title":"Learning More with Less: Self-Supervised Approaches for Low-Resource Speech Emotion Recognition","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2506.08493","title":"Context-aware TFL: A Universal Context-aware Contrastive Learning Framework for Temporal Forgery Localization","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2508.02000","title":"Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2112.10950","title":"Augmented Contrastive Self-Supervised Learning for Audio Invariant Representations","created":"2021-12-21","cited_by_count":1,"area":null},{"id":"2203.13628","title":"DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning","created":"2022-03-25","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":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2407.11168","title":"Efficient Unsupervised Visual Representation Learning with Explicit Cluster Balancing","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2506.05851","title":"DeepFake Doctor: Diagnosing and Treating Audio-Video Fake Detection","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2509.18424","title":"Scattering Transformer: A Training-Free Transformer Architecture for Heart Murmur Detection","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2605.14231","title":"AudioMosaic: Contrastive Masked Audio Representation Learning","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2306.05915","title":"Speaker Embeddings as Individuality Proxy for Voice Stress Detection","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2403.09579","title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2404.09504","title":"Learning Tracking Representations from Single Point Annotations","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2502.02118","title":"BRIDLE: Generalized Self-supervised Learning with Quantization","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2502.04899","title":"Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2502.15307","title":"Road Traffic Sign Recognition method using Siamese network Combining Efficient-CNN based Encoder","created":"2025-02-21","cited_by_count":0,"area":null},{"id":"2502.19071","title":"MCLRL: A Multi-Domain Contrastive Learning with Reinforcement Learning Framework for Few-Shot Modulation Recognition","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2509.15570","title":"Contrastive Learning with Spectrum Information Augmentation in Abnormal Sound Detection","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2512.13880","title":"Privacy-Enhancing Infant Cry Classification with Federated Transformers and Denoising Regularization","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2602.16305","title":"BAT: Better Audio Transformer Guided by Convex Gated Probing","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2606.29901","title":"Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.30356","title":"OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.00902","title":"MG-RWKV: Multi-Grained Context-Aware RWKV for Temporal Forgery Localization","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.04472","title":"EVAS: Efficient Multimodal Temporal Forgery Localization via Audio-Visual Synergy and Steered Boundary Calibration","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2608.30456","title":"Self-Supervised Pretext Tasks for Infant Cry Analysis: A Controlled Comparison and a Cautionary Result on Donateacry","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.11986","title":"Unlabeled Echoes: Pseudo-Labels and Genus-Aware Smoothing for Bat Call Recognition","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.15067","title":"Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation","created":"2026-09-14","cited_by_count":0,"area":null}],"next_cursor":null}