arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12290cs.SDcs.AIeess.AS
收藏

深度学习在音乐创作中的应用

Music Composition with Deep Learning: A Review

Universidad de Zaragoza(萨拉戈萨大学)

Carlos Hernandez-Olivan, Jose R. Beltran

摘要:

创作一件复杂的艺术作品,如音乐作品,需要展现出真正的创造力,而创造力取决于与音乐语言层次相关的各种因素。音乐生成一直面临着数学方法,最近,深度学习模型被用于其他领域,如计算机视觉。在本文中,我们希望将基于人工智能的音乐创作模型与人类音乐创作和创造力过程之间的现有关系置于上下文中。我们概述了最近用于音乐创作的深度学习模型,并从理论角度将这些模型与音乐创作过程进行了比较。我们试图通过分析当前深度学习模型生成具有创造力的音乐的能力或人工智能与人类作曲过程之间的相似性等来回答一些与此任务最相关的开放性问题。

英文摘要:

Generating a complex work of art such as a musical composition requires exhibiting true creativity that depends on a variety of factors that are related to the hierarchy of musical language. Music generation have been faced with Algorithmic methods and recently, with Deep Learning models that are being used in other fields such as Computer Vision. In this paper we want to put into context the existing relationships between AI-based music composition models and human musical composition and creativity processes. We give an overview of the recent Deep Learning models for music composition and we compare these models to the music composition process from a theoretical point of view. We have tried to answer some of the most relevant open questions for this task by analyzing the ability of current Deep Learning models to generate music with creativity or the similarity between AI and human composition processes, among others.

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。

↑