{"total":159,"rows":[{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616,"area":null},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388,"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":"2110.09784","title":"SSAST: Self-Supervised Audio Spectrogram Transformer","created":"2021-10-19","cited_by_count":169,"area":null},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106,"area":null},{"id":"2105.05837","title":"When Does Contrastive Visual Representation Learning Work?","created":"2021-05-12","cited_by_count":92,"area":null},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2102.01243","title":"PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation","created":"2021-02-02","cited_by_count":82,"area":null},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82,"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":"2106.05933","title":"PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition","created":"2021-06-10","cited_by_count":53,"area":null},{"id":"2201.04309","title":"Robust Contrastive Learning against Noisy Views","created":"2022-01-12","cited_by_count":45,"area":null},{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"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":"2203.14098","title":"Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation","created":"2022-03-26","cited_by_count":37,"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":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2306.00452","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","created":"2023-06-01","cited_by_count":28,"area":null},{"id":"2112.11450","title":"Max-Margin Contrastive Learning","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2206.02353","title":"Beyond Just Vision: A Review on Self-Supervised Representation Learning on Multimodal and Temporal Data","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"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":"2204.00616","title":"Simplicial Embeddings in Self-Supervised Learning and Downstream Classification","created":"2022-04-01","cited_by_count":24,"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":"2208.00467","title":"COCOA: Cross Modality Contrastive Learning for Sensor Data","created":"2022-07-31","cited_by_count":21,"area":null},{"id":"2305.14579","title":"Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning","created":"2023-05-23","cited_by_count":17,"area":null},{"id":"2308.14456","title":"Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads","created":"2023-08-28","cited_by_count":17,"area":null},{"id":"2105.07566","title":"Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification","created":"2021-05-17","cited_by_count":16,"area":null},{"id":"2105.09270","title":"Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?","created":"2021-05-19","cited_by_count":16,"area":null},{"id":"2210.16192","title":"Pretraining Respiratory Sound Representations using Metadata and Contrastive Learning","created":"2022-10-27","cited_by_count":15,"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":"2404.16969","title":"COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations","created":"2024-04-25","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":"2208.09378","title":"Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels","created":"2022-08-19","cited_by_count":13,"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":"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":"2312.15824","title":"Self-Supervised Learning for Few-Shot Bird Sound Classification","created":"2023-12-25","cited_by_count":11,"area":null},{"id":"2510.16548","title":"NeurIPT: Foundation Model for Neural Interfaces","created":"2025-10-18","cited_by_count":11,"area":null},{"id":"2110.09890","title":"Multi-Modal Pre-Training for Automated Speech Recognition","created":"2021-10-12","cited_by_count":10,"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":"2106.02443","title":"Teaching keyword spotters to spot new keywords with limited examples","created":"2021-06-04","cited_by_count":9,"area":null},{"id":"2305.14035","title":"Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2309.11845","title":"TMac: Temporal Multi-Modal Graph Learning for Acoustic Event Classification","created":"2023-09-21","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":"2404.15854","title":"CLAD: Robust Audio Deepfake Detection Against Manipulation Attacks with Contrastive Learning","created":"2024-04-24","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":"2208.06270","title":"RenyiCL: Contrastive Representation Learning with Skew Renyi Divergence","created":"2022-08-12","cited_by_count":8,"area":null},{"id":"2208.12238","title":"Supervised Contrastive Learning for Affect Modelling","created":"2022-08-25","cited_by_count":8,"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":"2107.00594","title":"Pretext Tasks selection for multitask self-supervised speech representation learning","created":"2021-07-01","cited_by_count":7,"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":"2205.10227","title":"Label Anchored Contrastive Learning for Language Understanding","created":"2022-04-26","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":"2209.07518","title":"Distribution Aware Metrics for Conditional Natural Language Generation","created":"2022-09-15","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":"2309.07200","title":"Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck","created":"2023-09-13","cited_by_count":6,"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":"2107.06877","title":"Federated Self-Training for Semi-Supervised Audio Recognition","created":"2021-07-14","cited_by_count":5,"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":"2210.01322","title":"Representing Spatial Trajectories as Distributions","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2210.12874","title":"Global Contrastive Batch Sampling via Optimization on Sample Permutations","created":"2022-10-23","cited_by_count":5,"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":"2311.16535","title":"Contrastive encoder pre-training-based clustered federated learning for heterogeneous data","created":"2023-11-28","cited_by_count":5,"area":null},{"id":"2402.15569","title":"Toward Fully Self-Supervised Multi-Pitch Estimation","created":"2024-02-23","cited_by_count":5,"area":null},{"id":"2404.09259","title":"FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity","created":"2024-04-14","cited_by_count":5,"area":null},{"id":"2406.02361","title":"Using Self-supervised Learning Can Improve Model Fairness","created":"2024-06-04","cited_by_count":5,"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":"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":"2207.07935","title":"Visually-aware Acoustic Event Detection using Heterogeneous Graphs","created":"2022-07-16","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":"2306.04374","title":"Label Aware Speech Representation Learning For Language Identification","created":"2023-06-07","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":"2402.12846","title":"ConVQG: Contrastive Visual Question Generation with Multimodal Guidance","created":"2024-02-20","cited_by_count":4,"area":null},{"id":"2404.06776","title":"Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Data","created":"2024-04-10","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":"2405.08679","title":"Investigating Design Choices in Joint-Embedding Predictive Architectures for General Audio Representation Learning","created":"2024-05-14","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":"2409.15672","title":"Language-based Audio Moment Retrieval","created":"2024-09-24","cited_by_count":4,"area":null},{"id":"2505.19863","title":"FruitNeRF++: A Generalized Multi-Fruit Counting Method Utilizing Contrastive Learning and Neural Radiance Fields","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2104.07388","title":"Conditional independence for pretext task selection in Self-supervised speech representation learning","created":"2021-04-15","cited_by_count":3,"area":null},{"id":"2111.00379","title":"EfficientWord-Net: An Open Source Hotword Detection Engine based on One-shot Learning","created":"2021-10-31","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":"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":"2407.08647","title":"From Real to Cloned Singer Identification","created":"2024-07-11","cited_by_count":3,"area":null},{"id":"2409.17656","title":"Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection","created":"2024-09-26","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":"2508.01488","title":"PESTO: Real-Time Pitch Estimation with Self-supervised Transposition-equivariant Objective","created":"2025-08-02","cited_by_count":3,"area":null},{"id":"2202.02112","title":"Musical Audio Similarity with Self-supervised Convolutional Neural Networks","created":"2022-02-04","cited_by_count":2,"area":null},{"id":"2204.08887","title":"Cross-Lingual Phrase Retrieval","created":"2022-04-19","cited_by_count":2,"area":null},{"id":"2302.03432","title":"SimCon Loss with Multiple Views for Text Supervised Semantic Segmentation","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2303.02665","title":"Heterogeneous Graph Learning for Acoustic Event Classification","created":"2023-03-05","cited_by_count":2,"area":null},{"id":"2306.01864","title":"Discovering COVID-19 Coughing and Breathing Patterns from Unlabeled Data Using Contrastive Learning with Varying Pre-Training Domains","created":"2023-06-02","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}],"next_cursor":"100"}