// Link · 28 January 2026

TalkNet-ASD: The “Who’s Talking?” Model for Any Video

TalkNet-ASD is an audio-visual active speaker detection model that labels speaking faces and outputs JSON speaker tracks for real-world footage.

@hacker-noon · hackernoon.com

Hacker Noon@hacker-noon

Discussion 0

Got something to say?

or to join the conversation.

Learn to build with AI and grow with people doing the same — it's free.