arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2110.05765cs.SDcs.LGcs.MMeess.AS
收藏

音乐情感传递

Music Sentiment Transfer

Rice University(莱斯大学);Cornell University(康奈尔大学);University of Rochester(罗切斯特大学)

Miles Sigel, Michael Zhou, Jiebo Luo

摘要:

音乐情感传递是一个全新的任务。情感转移是大量研究的风格转移任务的自然演变,因为情感转移植根于将源的情感应用于目标媒体的新情感;然而与风格转移相比,情感转移在图像上的研究很少。音乐情感迁移试图将情感迁移的高层次目标应用于音乐领域。我们提出CycleGAN来桥接不同的域。为了使用网络,我们选择使用符号,数字,数据作为音乐格式。通过使用循环一致性丢失,我们能够创建一对一映射,以保留源数据的内容和真实性。结果和文献表明,由于音乐的时间特征和缺乏现有数据集,音乐情感传递的任务比图像情感传递更困难。

英文摘要:

Music sentiment transfer is a completely novel task. Sentiment transfer is a natural evolution of the heavily-studied style transfer task, as sentiment transfer is rooted in applying the sentiment of a source to be the new sentiment for a target piece of media; yet compared to style transfer, sentiment transfer has been only scantily studied on images. Music sentiment transfer attempts to apply the high level objective of sentiment transfer to the domain of music. We propose CycleGAN to bridge disparate domains. In order to use the network, we choose to use symbolic, MIDI, data as the music format. Through the use of a cycle consistency loss, we are able to create one-to-one mappings that preserve the content and realism of the source data. Results and literature suggest that the task of music sentiment transfer is more difficult than image sentiment transfer because of the temporal characteristics of music and lack of existing datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑