JEN-1: Text-Guided Universal Music Generation with Omnidirectional Diffusion Models
This addresses the challenge of generating high-quality music from text descriptions, which is significant for creative applications, though it appears incremental as it builds on existing diffusion models.
The paper tackles text-to-music generation by introducing JEN-1, a diffusion model that achieves superior performance in text-music alignment and music quality compared to state-of-the-art methods, while maintaining computational efficiency.
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 https://jenmusic.ai/audio-demos