{"total":42,"rows":[{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"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":"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":"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":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53,"area":null},{"id":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39,"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":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"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":"2104.06517","title":"Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition","created":"2021-04-13","cited_by_count":15,"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":"2108.12955","title":"Unsupervised Learning of Deep Features for Music Segmentation","created":"2021-08-30","cited_by_count":12,"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":"2203.01829","title":"A Brief Overview of Unsupervised Neural Speech Representation Learning","created":"2022-03-01","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":"2106.08686","title":"Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study","created":"2021-06-16","cited_by_count":8,"area":null},{"id":"2107.08248","title":"Learning De-identified Representations of Prosody from Raw Audio","created":"2021-07-17","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":"2105.02132","title":"Self-Supervised Learning from Automatically Separated Sound Scenes","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2203.11997","title":"Federated Self-Supervised Learning for Acoustic Event Classification","created":"2022-03-22","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":"2210.01322","title":"Representing Spatial Trajectories as Distributions","created":"2022-10-04","cited_by_count":5,"area":null},{"id":"2109.11086","title":"Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora","created":"2021-09-23","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":"2102.05151","title":"Enhancing Audio Augmentation Methods with Consistency Learning","created":"2021-02-09","cited_by_count":3,"area":null},{"id":"2205.13064","title":"Urban Rhapsody: Large-scale exploration of urban soundscapes","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2309.11516","title":"Private Matrix Factorization with Public Item Features","created":"2023-09-17","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":"2209.06633","title":"Integrating Form and Meaning: A Multi-Task Learning Model for Acoustic Word Embeddings","created":"2022-09-14","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":"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":"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":"2401.18057","title":"Rank Supervised Contrastive Learning for Time Series Classification","created":"2024-01-31","cited_by_count":1,"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":"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":"2409.14043","title":"ECHO: Environmental Sound Classification with Hierarchical Ontology-guided Semi-Supervised Learning","created":"2024-09-21","cited_by_count":0,"area":null},{"id":"2503.22063","title":"Arch-VQ: Discrete Architecture Representation Learning with Autoregressive Priors","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2509.13285","title":"Contrastive timbre representations for musical instrument and synthesizer retrieval","created":"2025-09-16","cited_by_count":0,"area":null}],"next_cursor":null}