Official implementation of Whisfusion - the first Diffusion Transformer ASR framework that fuses a Whisper encoder with a diffusion decoder for faster, non-autoregressive transcription.

Abstract: Recent advances in artificial intelligence (AI) models, such as large language models and diffusion models, have shown significant potential in semantic communication by reconstructing ...

Abstract: With the rapid development of intelligent transportation systems and growing emphasis on driver safety, real-time detection of driver drowsiness has become a critical area of research. This ...

Customer stories Events & webinars Ebooks & reports Business insights GitHub Skills ...

Synthesizing realistic audio, images, and videos using algorithms has always been essential in Signal Processing, Computer Graphics, and Computer Vision. When using pre-artificial intelligence (AI) ...

The hierarchical diffusion model requires effective conditioning on both spatial perception and proprioceptive states. A naïve concatenation of conditioning variables with action sequences is ...