论文标题
Jukebox：音乐的生成模型
Jukebox: A Generative Model for Music
论文作者
论文摘要
我们介绍了Jukebox，该模型在原始音频域中生成音乐。我们使用多尺度的VQ-VAE来处理原始音频的长篇小说，以将其压缩到离散代码，并使用自动回归变压器进行建模。我们表明，大规模的组合模型可以产生高保真和多样的歌曲，并连贯多达几分钟。我们可以根据艺术家和流派进行条件，以引导音乐和人声风格，并以不一致的歌词来使唱歌更加可控。我们将在https://jukebox.openai.com上发布数千个非樱桃采集样本，以及https://github.com/openai/jukebox上的模型权重和代码
We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive Transformers. We show that the combined model at scale can generate high-fidelity and diverse songs with coherence up to multiple minutes. We can condition on artist and genre to steer the musical and vocal style, and on unaligned lyrics to make the singing more controllable. We are releasing thousands of non cherry-picked samples at https://jukebox.openai.com, along with model weights and code at https://github.com/openai/jukebox
