Using a Language Model to Generate Music in its Symbolic Domain while Controlling its Perceived Emotion-Reference-Cited by-同舟云学术

Using a Language Model to Generate Music in its Symbolic Domain while Controlling its Perceived Emotion

Author:

Imasato Naomi¹^ORCID,Miyazawa Kazuki¹^ORCID,Duncan Caitlin¹,Nagai Takayuki¹^ORCID

Affiliation:

1. Graduate School of Engineering Science, Osaka University, Osaka, Japan

Funder

JST Moonshot R&D

Grant-in-Aid for Scientific Research on Innovative Areas

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

General Engineering,General Materials Science,General Computer Science,Electrical and Electronic Engineering

Link

Reference46 articles.

1. VideoGPT: Video generation using VQ-VAE and transformers;yan;arXiv 2104 10157,2021

2. Music SketchNet: Controllable music generation via factorized representations of pitch and rhythm;chen;arXiv 2008 01291,2020

3. Generative pretraining from pixels;chen;Proc 37th Int Conf Mach Learn,2020

4. A hierarchical latent vector model for learning long-term structure in music;roberts;arXiv 1803 05428,2018

Cited by 6 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. AI-Driven ChatGPT Applications for Enhancing Music Education;Transactions on Computer Science and Intelligent Systems Research;2024-08-12

4. Musicological Interpretability in Generative Transformers;2023 4th International Symposium on the Internet of Sounds;2023-10-26

5. A Comparative Evaluation on Melody Generation of Large Language Models;2023 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia);2023-10-23