Seed-Music：高质量且可控音乐生成的统一框架
声音
2024-09-20 v3 音频与语音处理
摘要
我们介绍Seed-Music，一个能够产生高质量音乐并实现细粒度风格控制的音乐生成系统套件。我们的统一框架利用自回归语言建模和扩散方法，支持两种关键的音乐创作工作流程：受控音乐生成和后期制作编辑。对于受控音乐生成， our system enables vocal music generation with performance controls from multi-modal inputs, 包括风格描述、音频参考、音乐谱分和语音提示。对于后期制作编辑, our system offers interactive tools for editing lyrics and vocal melodies directly in the generated audio. 我们鼓励读者访问 https://team.doubao.com/seed-music 聆听演示音频示例。
引用
@article{arxiv.2409.09214,
title = {Seed-Music: A Unified Framework for High Quality and Controlled Music Generation},
author = {Ye Bai and Haonan Chen and Jitong Chen and Zhuo Chen and Yi Deng and Xiaohong Dong and Lamtharn Hantrakul and Weituo Hao and Qingqing Huang and Zhongyi Huang and Dongya Jia and Feihu La and Duc Le and Bochen Li and Chumin Li and Hui Li and Xingxing Li and Shouda Liu and Wei-Tsung Lu and Yiqing Lu and Andrew Shaw and Janne Spijkervet and Yakun Sun and Bo Wang and Ju-Chiang Wang and Yuping Wang and Yuxuan Wang and Ling Xu and Yifeng Yang and Chao Yao and Shuo Zhang and Yang Zhang and Yilin Zhang and Hang Zhao and Ziyi Zhao and Dejian Zhong and Shicen Zhou and Pei Zou},
journal= {arXiv preprint arXiv:2409.09214},
year = {2024}
}
备注
Seed-Music technical report, 20 pages, 5 figures