{"total":57,"rows":[{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287,"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":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77,"area":null},{"id":"2111.03017","title":"MT3: Multi-Task Multitrack Music Transcription","created":"2021-11-04","cited_by_count":71,"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":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"area":null},{"id":"2310.07160","title":"LLark: A Multimodal Instruction-Following Language Model for Music","created":"2023-10-11","cited_by_count":29,"area":null},{"id":"2212.01884","title":"Melody transcription via generative pre-training","created":"2022-12-04","cited_by_count":24,"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":"2211.01317","title":"Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming","created":"2022-11-02","cited_by_count":17,"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":"2402.09871","title":"MuChin: A Chinese Colloquial Description Benchmark for Evaluating Language Models in the Field of Music","created":"2024-02-15","cited_by_count":16,"area":null},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15,"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":"2410.00872","title":"Do Music Generation Models Encode Music Theory?","created":"2024-10-01","cited_by_count":13,"area":null},{"id":"2110.05798","title":"Adapting TTS models For New Speakers using Transfer Learning","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2301.08562","title":"Latent Autoregressive Source Separation","created":"2023-01-09","cited_by_count":12,"area":null},{"id":"2606.01802","title":"MOSS-Audio Technical Report","created":"2026-06-01","cited_by_count":11,"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":"2508.04651","title":"Live Music Models","created":"2025-08-06","cited_by_count":10,"area":null},{"id":"2410.15573","title":"OpenMU: Your Swiss Army Knife for Music Understanding","created":"2024-10-21","cited_by_count":9,"area":null},{"id":"2312.11234","title":"Perceptual Musical Features for Interpretable Audio Tagging","created":"2023-12-18","cited_by_count":7,"area":null},{"id":"2206.10805","title":"Jointist: Joint Learning for Multi-instrument Transcription and Its Applications","created":"2022-06-22","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":"2305.19602","title":"Learning Music Sequence Representation from Text Supervision","created":"2023-05-31","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":"2210.01719","title":"Learning Temporal Resolution in Spectrogram for Audio Classification","created":"2022-10-04","cited_by_count":4,"area":null},{"id":"2502.12031","title":"Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning","created":"2025-02-17","cited_by_count":4,"area":null},{"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":"2302.00286","title":"Jointist: Simultaneous Improvement of Multi-instrument Transcription and Music Source Separation via Joint Training","created":"2023-02-01","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":"2506.17055","title":"Universal Music Representations? Evaluating Foundation Models on World Music Corpora","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2405.09286","title":"MVBIND: Self-Supervised Music Recommendation For Videos Via Embedding Space Binding","created":"2024-05-15","cited_by_count":2,"area":null},{"id":"2408.07184","title":"A New Dataset, Notation Software, and Representation for Computational Schenkerian Analysis","created":"2024-08-13","cited_by_count":2,"area":null},{"id":"2411.02551","title":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2506.17818","title":"CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning","created":"2025-06-21","cited_by_count":2,"area":null},{"id":"2110.13071","title":"Unsupervised Source Separation By Steering Pretrained Music Models","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2306.12714","title":"Toward Leveraging Pre-Trained Self-Supervised Frontends for Automatic Singing Voice Understanding Tasks: Three Case Studies","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2407.02156","title":"Towards Training Music Taggers on Synthetic Data","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2409.09378","title":"Prevailing Research Areas for Music AI in the Era of Foundation Models","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2509.08283","title":"Segment Transformer: AI-Generated Music Detection via Music Structural Analysis","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2510.16273","title":"MuseTok: Symbolic Music Tokenization for Generation and Semantic Understanding","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2602.10058","title":"Evaluating Disentangled Representations for Controllable Music Generation","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2207.09145","title":"GAFX: A General Audio Feature eXtractor","created":"2022-07-19","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":"2405.12847","title":"A Dataset and Baselines for Measuring and Predicting the Music Piece Memorability","created":"2024-05-21","cited_by_count":0,"area":null},{"id":"2409.15545","title":"Addressing Emotion Bias in Music Emotion Recognition and Generation with Frechet Audio Distance","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2507.04776","title":"Improving BERT for Symbolic Music Understanding Using Token Denoising and Pianoroll Prediction","created":"2025-07-07","cited_by_count":0,"area":null},{"id":"2510.04688","title":"A Study on the Data Distribution Gap in Music Emotion Recognition","created":"2025-10-06","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":"2608.03050","title":"Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.14819","title":"What Makes a Good Layer? Assessing the Layer-Wise Intrinsic Properties of Music Foundation Models","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2610.15957","title":"Harmonic Representations in Symbolic Music Transformers are Localized and Controllable","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}