In recent years, there has been an increased popularity in image and speech
generation using diffusion models. However, directly generating music waveforms
from free-form text prompts is still under-explored. In this paper, we propose
the first text-to-waveform music generation model that can receive arbitrary
texts using diffusion models. We incorporate the free-form textual prompt as
the condition to guide the waveform generation process of diffusion models. To
solve the problem of lacking such text-music parallel data, we collect a
dataset of text-music pairs from the Internet with weak supervision. Besides,
we compare the effect of two prompt formats of conditioning texts (music tags
and free-form texts) and prove the superior performance of our method in terms
of text-music relevance. We further demonstrate that our generated music in the
waveform domain outperforms previous works by a large margin in terms of
diversity, quality, and text-music relevance.

本文提出了一种使用扩散模型的文本到音频波形音乐生成模型，通过收集匹配的文本 - 音乐数据集，证明了自由格式文本提示的有效性，提高了波形产生的相关性，并且其生成的音乐优于以往的作品，具有更高的多样性、质量和文本 - 音乐相关性。