Opening book details…
Can I read AudioX: Unified Diffusion for Audio Generation on EtoBox?
AudioX: Unified Diffusion for Audio Generation by zhouyuqiuabc is a document available to read on EtoBox.
What is AudioX: Unified Diffusion for Audio Generation about?
AudioX is a unified Diffusion Transformer model designed for Anything-to-Audio and Music Generation, addressing limitations in existing approaches by integrating diverse input modalities such as text, video, image, and audio. It utilizes a multi-modal masked training strategy and is supported by two comprehensive datasets: vggsound-caps and V2M-caps, which enhance its capability to generate high-quality audio and music. Extensive experiments demonstrate that AudioX outperforms state-of-the-art specialized m
- Author
- zhouyuqiuabc
- Language
- EN