Skip to content

Latest commit

 

History

History
executable file
·
38 lines (30 loc) · 7.26 KB

index.md

File metadata and controls

executable file
·
38 lines (30 loc) · 7.26 KB
layout
default

Abstract

The Song Generation task aims to synthesize music composed of vocals and accompaniment from given lyrics. While the existing method, Jukebox, has explored this task, its constrained control over the generations often leads to deficiency in music performance. To mitigate the issue, we introduce an important concept from music composition, namely chords, to song generation networks. Chords form the foundation of accompaniment and provide vocal melody with associated harmony. Given the inaccuracy of automatic chord extractors, we devise a robust cross-attention mechanism augmented with dynamic weight sequence to integrate extracted chord information into song generations and reduce frame-level flaws, and propose a novel model termed Chord-Conditioned Song Generator (CSG) based on it. Experimental evidence demonstrates our proposed method outperforms other approaches in terms of musical performance and control precision of generated songs.

Music Sample

We show the songs generated by proposed CSG and other methods, conditioned by unseen lyrics and specified chords.

<style> table { width: 100%; } td { vertical-align: middle; /* 将单元格内容对齐到顶部 */ padding: 10px; /* 添加单元格内部的填充 */ } .large-cell { width: 500px; /* 调整最后一列的行距 */ } .large-img { width: 500px; /* 设置图片高度 */ } </style>
Lyrics Chords reference chords Jukebox GPT-only concatenation cross-attention proposed spectrogram of proposed
But thoughts, the fields to see and prize; Else may the silent feet. 6-5-4-1 (A:min-G:maj-F:maj-C:maj) Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element.
Don't you know it's gonna be alright. 6-4-5-1 (A:min-F:maj-G:maj-C:maj) Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element.
When I get lunch and eat my food, I hope that my model will Reason. 1-5-6-4 (C:maj-G:maj-A:min-F:maj) Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element.
Just as long as I am there, I'll be there in your night. 2-6-5-1 (D:min-A:min-G:maj-C:maj) Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element.
The darkest evening of the year. 4-5-3-6 (F:maj-G:maj-E:min-A:min) Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element.
Dead puppets may, move in the bright and glorious day. 1-2-3-4 (C:maj-D:min-E:min-F:maj) Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element. Your browser does not support the audio element.