Can I read MelodyGLM: Multi-task Pre-training for Symbolic Melody Generation on EtoBox?

MelodyGLM: Multi-task Pre-training for Symbolic Melody Generation by Wu, Xinda; Huang, Zhijie; Zhang, Kejun; Yu, Jiaxing; Tan, Xu; Zhang, Tieyao; Wang, Zihao; Sun, Lingyun is a scholarly article available to read on EtoBox.

What is MelodyGLM: Multi-task Pre-training for Symbolic Melody Generation about?

Pre-trained language models have achieved impressive results in various music understanding and generation tasks. However, existing pre-training methods for symbolic melody generation struggle to capture multi-scale, multi-dimensional structural information in note sequences, due to the domain knowledge discrepancy between text and music. Moreover, the lack of available large-scale symbolic melody datasets limits the pre-training improvement. In this paper, we propose MelodyGLM, a multi-task pre-training framework for generating melodies with long-term structure. We design the melodic n-gram and long span sampling strategies to create local and global blank infilling tasks for modeling the local and global structures in melodies. Specifically, we incorporate pitch n-grams, rhythm n-grams, and their combined n-grams into the melodic n-gram blank infilling tasks for modeling the multi-dimensional structures in melodies. To this end, we have constructed a large-scale symbolic melody dataset, MelodyNet, containing more than 0.4 million melody pieces. MelodyNet is utilized for large-scale pre-training and domain-specific n-gram lexicon construction. Both subjective and objective evaluat

Author

Wu, Xinda; Huang, Zhijie; Zhang, Kejun; Yu, Jiaxing; Tan, Xu; Zhang, Tieyao; Wang, Zihao; Sun, Lingyun

Published

2023

Language

EN