arXiv - CSCL: "Auffusion: Leveraging the Power of Diffusion and …" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

Auffusion: Leveraging the Power of Diffusion and Large Language Models for Text-to-Audio Generation. (arXiv:2401.01044v1 [cs.SD])

http://arxiv.org/abs/2401.01044 #arXiv #NLProc

Jan 03, 2024, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation