{"total":82,"rows":[{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213,"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":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2501.01108","title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","created":"2025-01-02","cited_by_count":68,"area":null},{"id":"2107.05677","title":"Codified audio language modeling learns useful representations for music information retrieval","created":"2021-07-12","cited_by_count":64,"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":"2408.14340","title":"Foundation Models for Music: A Survey","created":"2024-08-26","cited_by_count":37,"area":"diffusion"},{"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":"2408.06500","title":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","created":"2024-08-12","cited_by_count":33,"area":"diffusion"},{"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":"2212.02508","title":"MAP-Music2Vec: A Simple and Effective Baseline for Self-Supervised Music Audio Representation Learning","created":"2022-12-05","cited_by_count":22,"area":null},{"id":"2211.02247","title":"Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects","created":"2022-11-04","cited_by_count":18,"area":null},{"id":"2110.09127","title":"SpecTNT: a Time-Frequency Transformer for Music Audio","created":"2021-10-18","cited_by_count":16,"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":"2112.04214","title":"Learning music audio representations via weak language supervision","created":"2021-12-08","cited_by_count":13,"area":null},{"id":"2401.14542","title":"Exploring Musical Roots: Applying Audio Embeddings to Empower Influence Attribution for a Generative Music Model","created":"2024-01-25","cited_by_count":13,"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":"2209.14458","title":"The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling","created":"2022-09-28","cited_by_count":10,"area":null},{"id":"2407.14364","title":"Towards Assessing Data Replication in Music Generation with Music Similarity Metrics on Raw Audio","created":"2024-07-19","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":"2506.23869","title":"Scaling Self-Supervised Representation Learning for Symbolic Piano Performance","created":"2025-06-30","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":"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":"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":"2202.08520","title":"End-to-end Music Remastering System Using Self-supervised and Adversarial Training","created":"2022-02-17","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":"2411.01135","title":"Music Foundation Model as Generic Booster for Music Downstream Tasks","created":"2024-11-02","cited_by_count":6,"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":"2305.19602","title":"Learning Music Sequence Representation from Text Supervision","created":"2023-05-31","cited_by_count":5,"area":null},{"id":"2306.17424","title":"Audio Embeddings as Teachers for Music Classification","created":"2023-06-30","cited_by_count":5,"area":"distill"},{"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":"2308.02249","title":"Finding Tori: Self-supervised Learning for Analyzing Korean Folk Song","created":"2023-08-04","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":"2505.22238","title":"Yambda-5B -- A Large-Scale Multi-modal Dataset for Ranking And Retrieval","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2305.01578","title":"Self-supervised learning for infant cry analysis","created":"2023-05-02","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":"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":"2501.17578","title":"Music2Latent2: Audio Compression with Summary Embeddings and Autoregressive Decoding","created":"2025-01-29","cited_by_count":4,"area":"diffusion"},{"id":"2504.00837","title":"A Survey on Music Generation from Single-Modal, Cross-Modal, and Multi-Modal Perspectives","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2505.16306","title":"Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2306.11898","title":"Relating tSNE and UMAP to Classical Dimensionality Reduction","created":"2023-06-20","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":"2501.07474","title":"Estimating Musical Surprisal in Audio","created":"2025-01-13","cited_by_count":3,"area":null},{"id":"2501.15900","title":"Investigating the Sensitivity of Pre-trained Audio Embeddings to Common Effects","created":"2025-01-27","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":"2108.09203","title":"Parsing Birdsong with Deep Audio Embeddings","created":"2021-08-20","cited_by_count":2,"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":"2309.15938","title":"Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation","created":"2023-09-27","cited_by_count":2,"area":null},{"id":"2311.07534","title":"Unsupervised Musical Object Discovery from Audio","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2506.23873","title":"Emergent musical properties of a transformer under contrastive self-supervised learning","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2511.05717","title":"Persian Musical Instruments Classification Using Polyphonic Data Augmentation","created":"2025-11-07","cited_by_count":2,"area":null},{"id":"2512.02652","title":"Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2309.00347","title":"Towards Contrastive Learning in Music Video Domain","created":"2023-09-01","cited_by_count":1,"area":null},{"id":"2309.01340","title":"MDSC: Towards Evaluating the Style Consistency Between Music and Dance","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2401.08902","title":"Similar but Faster: Manipulation of Tempo in Music Audio Embeddings for Tempo Prediction and Search","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2401.15323","title":"Music Auto-Tagging with Robust Music Representation Learned via Domain Adversarial Training","created":"2024-01-27","cited_by_count":1,"area":null},{"id":"2405.08538","title":"Self-Distillation Improves DNA Sequence Inference","created":"2024-05-14","cited_by_count":1,"area":"distill"},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2503.23128","title":"CrossMuSim: A Cross-Modal Framework for Music Similarity Retrieval with LLM-Powered Text Description Sourcing and Mining","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2605.03929","title":"PHALAR: Phasors for Learned Musical Audio Representations","created":"2026-05-05","cited_by_count":1,"area":null},{"id":"2607.00641","title":"What's a Credit Worth? A Market Framework for Attribution-Aware Compensation in Generative Music","created":"2026-07-01","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":"2208.09096","title":"Representation Learning for the Automatic Indexing of Sound Effects Libraries","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2209.02388","title":"Pathway to Future Symbiotic Creativity","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2210.15988","title":"Spectrograms Are Sequences of Patches","created":"2022-10-28","cited_by_count":0,"area":null},{"id":"2304.07449","title":"Self-supervised Auxiliary Loss for Metric Learning in Music Similarity-based Retrieval and Auto-tagging","created":"2023-04-15","cited_by_count":0,"area":null},{"id":"2408.12753","title":"Contrastive Representation Learning for Dynamic Link Prediction in Temporal Networks","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2411.19806","title":"Zero-shot Musical Stem Retrieval with Joint-Embedding Predictive Architectures","created":"2024-11-29","cited_by_count":0,"area":null},{"id":"2505.06042","title":"Learning Music Audio Representations With Limited Data","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2509.26291","title":"Representation-Based Data Quality Audits for Audio","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.22295","title":"VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2511.07205","title":"Twenty-Five Years of MIR Research: Achievements, Practices, Evaluations, and Future Challenges","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2601.09603","title":"Linear Complexity Self-Supervised Learning for Music Understanding with Random Quantizer","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2604.10021","title":"Masked Contrastive Pre-Training Improves Music Audio Key Detection","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2608.30974","title":"CoJEPA: Combining Contrastive Learning and JEPA for Global-Local Music Representations","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.00987","title":"On the Human and Computer Alignment of Attribute-Based Music Matches","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.11792","title":"AuraLuxMuse: Adaptive Fusion Modeling for Aesthetic Stage Lighting Design with Music and Expert Guidance","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}