DEEP LEARNING FOR MUSIC GENERATION. FOUR APPROACHES AND THEIR COMPARATIVE EVALUATION

被引：0
作者：
Paroiu, Razvan [1 ]
Trausan-matu, Stefan [2 ]
机构：
[1] Univ Politehn Bucuresti, Fac Automat & Comp Sci, Bucharest, Romania
[2] Univ Politehn Bucuresti, Romanian Acad Res Inst Artificial Intelligence, Acad Romanian Scientists, Fac Automat & Comp Sci, Bucharest, Romania
来源：
UNIVERSITY POLITEHNICA OF BUCHAREST SCIENTIFIC BULLETIN SERIES C-ELECTRICAL ENGINEERING AND COMPUTER SCIENCE | 2023年 / 85卷 / 04期
关键词：
neural networks; deep learning; transformer; Schillinger; sonification; GPT3;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
This paper introduces four different artificial intelligence algorithms for music generation and aims to compare these methods not only based on the aesthetic quality of the generated music but also on their suitability for specific applications. The first set of melodies is produced by a slightly modified visual transformer neural network that is used as a language model. The second set of melodies is generated by combining chat sonification with a classic transformer neural network (the same method of music generation is presented in a previous research), the third set of melodies is generated by combining the Schillinger rhythm theory together with a classic transformer neural network, and the fourth set of melodies is generated using GPT3 transformer provided by OpenAI. A comparative analysis is performed on the melodies generated by these approaches and the results indicate that significant differences can be observed between them and regarding the aesthetic value of them, GPT3 produced the most pleasing melodies, and the newly introduced Schillinger method proved to generate better sounding music than previous sonification methods.
引用
收藏
页码：15 / 28
页数：14
相关论文
共 26 条
  • [1] Absil Frans, 2015, A Guide to Schillinger's Theory of Rhythm
  • [2] Huang CZA, 2018, Arxiv, DOI arXiv:1809.04281
  • [3] Avignon symphonic orchestra [ORAP], 2023, plays AIVA: Symphonic Fantasy in A minor
  • [4] Brown TB, 2020, Arxiv, DOI arXiv:2005.14165
  • [5] Bahdanau D, 2016, Arxiv, DOI [arXiv:1409.0473, 10.48550/arXiv.1409.0473]
  • [6] Bakhtin M., 1984, Problems of Dostoevskys Poetics, DOI 10.5749/j.ctt22727z1
  • [7] Cho KYHY, 2014, Arxiv, DOI [arXiv:1406.1078, 10.48550/arXiv.1406.1078.]
  • [8] Devlin J, 2019, Arxiv, DOI arXiv:1810.04805
  • [9] Dong HW, 2022, Arxiv, DOI arXiv:2207.06983
  • [10] Dosovitskiy A, 2021, Arxiv, DOI [arXiv:2010.11929, DOI 10.48550/ARXIV.2010.11929]
123