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.

翻译：我们提出了MusicLM，这是一个能够根据文本描述（例如“被扭曲吉他即兴段衬托的宁静小提琴旋律”）生成高保真音乐的模型。MusicLM将条件音乐生成过程建模为层次化的序列到序列任务，并以24 kHz的采样率生成持续数分钟且保持一致的音频。实验表明，MusicLM在音频质量和对文本描述的遵循程度上均优于先前系统。此外，我们展示了MusicLM可以同时以文本和旋律为条件，从而能够根据文本说明中描述的风格转换吹口哨或哼唱的旋律。为支持未来研究，我们公开了MusicCaps数据集，该数据集包含5500对音乐-文本描述，并由人类专家提供了丰富的文本说明。