{"total":46,"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":"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":"2210.03799","title":"Supervised and Unsupervised Learning of Audio Representations for Music Understanding","created":"2022-10-07","cited_by_count":35,"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":"2310.06282","title":"MuseChat: A Conversational Music Recommendation System for Videos","created":"2023-10-10","cited_by_count":21,"area":null},{"id":"2206.07148","title":"It's Time for Artistic Correspondence in Music and Video","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2306.09327","title":"Language-Guided Music Recommendation for Video via Prompt Analogies","created":"2023-06-15","cited_by_count":18,"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":"2409.17864","title":"A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarios","created":"2024-09-26","cited_by_count":13,"area":null},{"id":"2207.11229","title":"Flow Moods: Recommending Music by Moods on Deezer","created":"2022-07-15","cited_by_count":11,"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":"2404.18470","title":"ECC Analyzer: Extract Trading Signal from Earnings Conference Calls using Large Language Model for Stock Performance Prediction","created":"2024-04-29","cited_by_count":9,"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":"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":"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":"2307.09795","title":"From West to East: Who can understand the music of the others better?","created":"2023-07-19","cited_by_count":5,"area":null},{"id":"2503.08147","title":"FilmComposer: LLM-Driven Music Production for Silent Film Clips","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2207.13909","title":"Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning","created":"2022-07-28","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2110.08862","title":"Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features","created":"2021-10-17","cited_by_count":3,"area":null},{"id":"2207.11231","title":"Learning Unsupervised Hierarchies of Audio Concepts","created":"2022-07-21","cited_by_count":3,"area":null},{"id":"2211.08379","title":"Music Instrument Classification Reprogrammed","created":"2022-11-15","cited_by_count":3,"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":"2411.02551","title":"PIAST: A Multimodal Piano Dataset with Audio, Symbolic and Text","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2305.11582","title":"What You Hear Is What You See: Audio Quality Metrics From Image Quality Metrics","created":"2023-05-19","cited_by_count":1,"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":"2310.04722","title":"A Holistic Evaluation of Piano Sound Quality","created":"2023-10-07","cited_by_count":1,"area":null},{"id":"2404.02342","title":"A Computational Analysis of Lyric Similarity Perception","created":"2024-04-02","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":"2409.07730","title":"Music auto-tagging in the long tail: A few-shot approach","created":"2024-09-12","cited_by_count":1,"area":null},{"id":"2110.04765","title":"Multi-task Learning with Metadata for Music Mood Classification","created":"2021-10-10","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":"2410.20352","title":"An approach to hummed-tune and song sequences matching","created":"2024-10-27","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":"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":"2601.11262","title":"Scalable Music Cover Retrieval Using Lyrics-Aligned Audio Embeddings","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.04293","title":"LabelBuddy: An Open Source Music and Audio Language Annotation Tagging Tool Using AI Assistance","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.28644","title":"Constructing Composite Features for Interpretable Music-Tagging","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2606.00125","title":"Multimodal Music Recommendation System using LLMs","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}