Late to the party, but still thrilled to announce that my paper with @MetaAI LA-VocE has been accepted to #ICASSP2023 🥳
It's an audio🔊-visual👀 speech💬 enhancement model that achieves state-of-the-art performance in low-SNR scenarios https://t.co/2GhGhiSRUL .
[1/5 🧵]
📢New paper
We are announcing ReVISE, the first universal audio-visual speech enhancement model powered by SSL.
paper: https://t.co/HsMVjhzzSy
demo: https://t.co/vS2JC3AJRj
w/ @adiyossLC@TalRemez@BowenSh08204149@_JacobDonley
First paper from my PhD is now online! Parenting and neighbouring in the consolidating city: The emotional geographies of sound in apartments w/ @profcgibson & @NataschaKlocker https://t.co/FvPR0y7L9L
At the huge China Hi Tech Fair in Shenzhen meeting colleagues from PKUSZ. Lot's of AI, VR and automation tech companies small and large - applications to health, environment, entertainment and manufacturing.