Abstract
We introduce MusicLM, a model generating high-fidelity music from text descriptions such as "a calming violin melody backed by a distorted guitar riff". MusicLM casts the process of conditional music generation as a hierarchical sequence-to-sequence modeling task, and it generates music at 24 kHz that remains consistent over several minutes. Our experiments show that MusicLM outperforms previous systems both in audio quality and adherence to the text description. Moreover, we demonstrate that MusicLM can be conditioned on both text and a melody in that it can transform whistled and hummed melodies according to the style described in a text caption. To support future research, we publicly release MusicCaps, a dataset composed of 5.5k music-text pairs, with rich text descriptions provided by human experts.
Abstract (translated)
我们介绍了音乐LM模型,一个从文本描述如“一个平静小提琴旋律伴随着一个失真吉他和弦”等生成高保真音乐的模型。音乐LM将条件音乐生成过程视为Hierarchical序列-to-序列建模任务,并生成24 kHz的音乐,在几分钟内保持一致性。我们的实验表明,音乐LM在音频质量和遵循文本描述方面比先前的系统更好。此外,我们证明了音乐LM可以基于文本和旋律进行条件,根据文本标题描述的风格改变Whistled和Humming旋律。为了支持未来的研究,我们公开发布了音乐Caps数据集,由人类专家提供丰富的文本描述。
URL
https://arxiv.org/abs/2301.11325
