An Unsupervised Methodology for Musical Style Translation

被引：2

作者：

Wang, Junhao ^{[1
]}

Jin, Cong ^{[1
]}

Zhao, Wei ^{[1
]}

Liu, Shan ^{[1
]}

Lv, Xin ^{[2
]}

机构：

[1] Commun Univ China, Sch Informat & Commun Engn, Beijing, Peoples R China

[2] Commun Univ China, Sch Animat & Digital Arts, Beijing, Peoples R China

来源：

2019 15TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND SECURITY (CIS 2019) | 2019年

基金：

国家重点研发计划; 中国国家自然科学基金;

关键词：

deep learning; symbolic music; style; domain; transfer;

D O I：

10.1109/CIS.2019.00053

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Deep learning techniques applied in image style transfer have shown great success. In the domain of music, this task can further aid musicians and music-generating AIs in the production of music. In this paper we present an unsupervised methodology for musical style transfer, which do not rely on strictly paired data to train. The model is capable of translating the style of symbolic music from the source domain to the target domain while mostly preserving the content and structure of input data. Output samples are evaluated by genre classifiers and show promising results.

引用

页码：216 / 220

页数：5

共 23 条

[1] [Anonymous], 2015, PROC CVPR IEEE
[2] [Anonymous], 2018, ARXIV180507848
[3] [Anonymous], 2018, ARXIV180907600
[4] Symbolic Music Genre Transfer with CycleGAN
Brunner, Gino
Wang, Yuyi
Wattenhofer, Roger
Zhao, Sumu
[J]. 2018 IEEE 30TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI), 2018, : 786 - 793
[5] Cifka O., 2019, ARXIV190702265
[6] Denton E, 2015, ADV NEUR IN, V28
[7] Dieleman S., 2016, ARXIV160903499
[8] Dong HW, 2018, AAAI CONF ARTIF INTE, P34
[9] Gatys L.A., 2015, arXiv, DOI DOI 10.1167/16.12.326
[10] Goodfellow IJ, 2014, ADV NEUR IN, V27, P2672

← 1 2 3 →