SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Jiaxing, Wu, Xinda, Xu, Yunfei, Zhang, Tieyao, Wu, Songruoyao, Ma, Le, Zhang, Kejun
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910761344827392
author Yu, Jiaxing
Wu, Xinda
Xu, Yunfei
Zhang, Tieyao
Wu, Songruoyao
Ma, Le
Zhang, Kejun
author_facet Yu, Jiaxing
Wu, Xinda
Xu, Yunfei
Zhang, Tieyao
Wu, Songruoyao
Ma, Le
Zhang, Kejun
contents Lyric-to-melody generation aims to automatically create melodies based on given lyrics, requiring the capture of complex and subtle correlations between them. However, previous works usually suffer from two main challenges: 1) lyric-melody alignment modeling, which is often simplified to one-syllable/word-to-one-note alignment, while others have the problem of low alignment accuracy; 2) lyric-melody harmony modeling, which usually relies heavily on intermediates or strict rules, limiting model's capabilities and generative diversity. In this paper, we propose SongGLM, a lyric-to-melody generation system that leverages 2D alignment encoding and multi-task pre-training based on the General Language Model (GLM) to guarantee the alignment and harmony between lyrics and melodies. Specifically, 1) we introduce a unified symbolic song representation for lyrics and melodies with word-level and phrase-level (2D) alignment encoding to capture the lyric-melody alignment; 2) we design a multi-task pre-training framework with hierarchical blank infilling objectives (n-gram, phrase, and long span), and incorporate lyric-melody relationships into the extraction of harmonized n-grams to ensure the lyric-melody harmony. We also construct a large-scale lyric-melody paired dataset comprising over 200,000 English song pieces for pre-training and fine-tuning. The objective and subjective results indicate that SongGLM can generate melodies from lyrics with significant improvements in both alignment and harmony, outperforming all the previous baseline methods.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18107
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Training
Yu, Jiaxing
Wu, Xinda
Xu, Yunfei
Zhang, Tieyao
Wu, Songruoyao
Ma, Le
Zhang, Kejun
Audio and Speech Processing
Artificial Intelligence
Sound
Lyric-to-melody generation aims to automatically create melodies based on given lyrics, requiring the capture of complex and subtle correlations between them. However, previous works usually suffer from two main challenges: 1) lyric-melody alignment modeling, which is often simplified to one-syllable/word-to-one-note alignment, while others have the problem of low alignment accuracy; 2) lyric-melody harmony modeling, which usually relies heavily on intermediates or strict rules, limiting model's capabilities and generative diversity. In this paper, we propose SongGLM, a lyric-to-melody generation system that leverages 2D alignment encoding and multi-task pre-training based on the General Language Model (GLM) to guarantee the alignment and harmony between lyrics and melodies. Specifically, 1) we introduce a unified symbolic song representation for lyrics and melodies with word-level and phrase-level (2D) alignment encoding to capture the lyric-melody alignment; 2) we design a multi-task pre-training framework with hierarchical blank infilling objectives (n-gram, phrase, and long span), and incorporate lyric-melody relationships into the extraction of harmonized n-grams to ensure the lyric-melody harmony. We also construct a large-scale lyric-melody paired dataset comprising over 200,000 English song pieces for pre-training and fine-tuning. The objective and subjective results indicate that SongGLM can generate melodies from lyrics with significant improvements in both alignment and harmony, outperforming all the previous baseline methods.
title SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Training
topic Audio and Speech Processing
Artificial Intelligence
Sound
url https://arxiv.org/abs/2412.18107