Music Phrase Inpainting Using Long-Term Representation and Contrastive Loss

Author:

Wei Shiqi1,Xia Gus2,Zhang Yixiao3,Lin Liwei2,Gao Weiguo4

Affiliation:

1. Fudan University,School of Data Science

2. New York University Shanghai,Music X lab

3. Queen Mary University of London,Centre for Digital Music

4. Fudan University,School of Mathematical Sciences

Publisher

IEEE

Reference19 articles.

1. Learning interpretable representation for controllable polyphonic music generation;wang;Proceedings of the 21th International Society for Music Information Retrieval Conference ISMIR,2020

2. Transformer VAE: A Hierarchical Model for Structure-Aware and Interpretable Music Representation Learning

3. MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment

4. Learning long-term music representations via hierarchical contextual constraints;wei;Proceedings of the 22nd International Society for Music Information Retrieval Conference ISMIR,2021

5. A simple framework for contrastive learning of visual representations;chen;Proceedings of the ICML International Conference on Machine Learning,2020

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Drawlody: Sketch-Based Melody Creation With Enhanced Usability and Interpretability;IEEE Transactions on Multimedia;2024

2. Generative Inpainting for Shapley-Value-Based Anomaly Explanation;Communications in Computer and Information Science;2024

3. Controllable Music Inpainting with Mixed-Level and Disentangled Representation;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

4. Fine-Tuning Music Generation with Reinforcement Learning Based on Transformer;2022 IEEE 16th International Conference on Anti-counterfeiting, Security, and Identification (ASID);2022-12-02

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3