Musical Composition Style Transfer via Disentangled Timbre Representations

Author:

Hung Yun-Ning1,Chiang I-Tung1,Chen Yi-An2,Yang Yi-Hsuan1

Affiliation:

1. Research Center for IT Innovation, Academia Sinica, Taiwan

2. KKBOX Inc., Taiwan

Abstract

Music creation involves not only composing the different parts (e.g., melody, chords) of a musical work but also arranging/selecting the instruments to play the different parts. While the former has received increasing attention, the latter has not been much investigated. This paper presents, to the best of our knowledge, the first deep learning models for rearranging music of arbitrary genres. Specifically, we build encoders and decoders that take a piece of polyphonic musical audio as input, and predict as output its musical score. We investigate disentanglement techniques such as adversarial training to separate latent factors that are related to the musical content (pitch) of different parts of the piece, and that are related to the instrumentation (timbre) of the parts per short-time segment. By disentangling pitch and timbre, our models have an idea of how each piece was composed and arranged. Moreover, the models can realize “composition style transfer” by rearranging a musical piece without much affecting its pitch content. We validate the effectiveness of the models by experiments on instrument activity detection and composition style transfer. To facilitate follow-up research, we open source our code at https://github.com/biboamy/instrument-disentangle.

Publisher

International Joint Conferences on Artificial Intelligence Organization

Cited by 11 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. A Novel Probabilistic Diffusion Model Based on the Weak Selection Mimicry Theory for the Generation of Hypnotic Songs;Mathematics;2023-07-30

2. Disentangling the Horowitz Factor: Learning Content and Style From Expressive Piano Performance;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

3. Note and Playing Technique Transcription of Electric Guitar Solos in Real-World Music Performance;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04

4. Difficulty-Aware Neural Band-to-Piano Score Arrangement based on Note- and Statistic-Level Criteria;ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2022-05-23

5. Audio-To-Symbolic Arrangement Via Cross-Modal Music Representation Learning;ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2022-05-23

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