4 papers
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer
Jiarui Hai, Yong Xu, Hao Zhang +4
We introduce EzAudio, a text-to-audio (T2A) generation framework designed to produce high-quality, natural-sounding sound effects. Core designs include: (1) We propose EzAudio-DiT,…
Towards Diverse and Efficient Audio Captioning via Diffusion Models
Manjie Xu, Chenxing Li, Xinyi Tu +4
We introduce Diffusion-based Audio Captioning (DAC), a non-autoregressive diffusion model tailored for diverse and efficient audio captioning. Although existing captioning models r…
STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment
Yong Ren, Chenxing Li, Manjie Xu +4
Visual and auditory perception are two crucial ways humans experience the world. Text-to-video generation has made remarkable progress over the past year, but the absence of harmon…
Video-to-Audio Generation with Hidden Alignment
Manjie Xu, Chenxing Li, Xinyi Tu +5
Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthr…