Music generation has attracted growing interest with the advancement of deep generative models. However, generating music conditioned on textual descriptions, known as text-to-music, remains challenging due to the complexity of musical structures and high sampling rate requirements. Despite the task's significance, prevailing generative models exhibit limitations in music quality, computational efficiency, and generalization. This paper introduces JEN-1, a universal high-fidelity model for text-to-music generation. JEN-1 is a diffusion model incorporating both autoregressive and non-autoregressive training. Through in-context learning, JEN-1 performs various generation tasks including text-guided music generation, music inpainting, and continuation. Evaluations demonstrate JEN-1's superior performance over state-of-the-art methods in text-music alignment and music quality while maintaining computational efficiency. Our demos are available at http://futureverse.com/research/jen/demos/jen1

翻译：音乐生成随着深度生成模型的发展引起了越来越多的关注。然而，基于文本描述生成音乐（即文本到音乐）由于音乐结构的复杂性和高采样率要求，仍然具有挑战性。尽管该任务具有重要意义，但当前的生成模型在音乐质量、计算效率和泛化能力方面存在局限性。本文介绍了JEN-1，一个用于文本到音乐生成的通用高保真模型。JEN-1是一种结合自回归和非自回归训练的扩散模型。通过上下文学习，JEN-1能够执行多种生成任务，包括文本引导的音乐生成、音乐修复和续写。评估结果表明，JEN-1在文本-音乐对齐和音乐质量方面优于现有最先进方法，同时保持了计算效率。我们的演示可在http://futureverse.com/research/jen/demos/jen1查看。