Crossmark

MLAT: a multi-level attention transformer capturing multi-level information in compound word encoding for symbolic music generation

Published Online: 2025-04-22

Authors

Zhou, Lianyu

Yin, Liang https://orcid.org/0000-0001-8212-0839
Qian, Yukun

Wang, Mingjiang
Funding

Funding for this research was provided by:

National Natural Science Foundation of China (62276076)

National Natural Science Foundation of China (62176102)

Guangdong Basic and Applied Basic Research Foundation (2023A1515140109)
License Information

Text and Data Mining valid from 2025-04-22

Version of Record valid from 2025-04-22
More Information

Article History

Received: 10 January 2025

Accepted: 7 April 2025

First Online: 22 April 2025

Declarations

:

: The authors declare that they have no competing interests.

Document is current