{"total":31,"rows":[{"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":"2306.10548","title":"MARBLE: Music Audio Representation Benchmark for Universal Evaluation","created":"2023-06-18","cited_by_count":38,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2506.12285","title":"CMI-Bench: A Comprehensive Benchmark for Evaluating Music Instruction Following","created":"2025-06-14","cited_by_count":17,"area":null},{"id":"2306.17103","title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","created":"2023-06-29","cited_by_count":15,"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":"2406.08809","title":"Are We There Yet? A Brief Survey of Music Emotion Prediction Datasets, Models and Outstanding Challenges","created":"2024-06-13","cited_by_count":7,"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":"2508.12709","title":"MATPAC++: Enhanced Masked Latent Prediction for Self-Supervised Audio Representation Learning","created":"2025-08-18","cited_by_count":6,"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":"2402.15569","title":"Toward Fully Self-Supervised Multi-Pitch Estimation","created":"2024-02-23","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":"2310.09853","title":"MERTech: Instrument Playing Technique Detection Using Self-Supervised Pretrained Model With Multi-Task Finetuning","created":"2023-10-15","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":"2404.09177","title":"An Experimental Comparison Of Multi-view Self-supervised Methods For Music Tagging","created":"2024-04-14","cited_by_count":4,"area":null},{"id":"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":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","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":"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":"2309.01340","title":"MDSC: Towards Evaluating the Style Consistency Between Music and Dance","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2401.08891","title":"Tempo estimation as fully self-supervised binary classification","created":"2024-01-17","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":"2512.17209","title":"Do Foundational Audio Encoders Understand Music Structure?","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2607.03296","title":"Taste-aware music retrieval from audio embeddings","created":"2026-07-03","cited_by_count":1,"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":"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":"2607.00777","title":"Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition","created":"2026-07-01","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}],"next_cursor":null}