Nov. 16, 2023, 11:38 a.m. | Jon Porter

The Verge - All Posts

SynthID works by converting audio into a visual spectogram and adding a visual watermark. | Image: Google

Audio created using Google DeepMind’s AI Lyria model, such as tracks made with YouTube’s new audio generation features, will be watermarked with SynthID to let people identify their AI-generated origins after the fact. In a blog post, DeepMind said the watermark shouldn’t be detectable by the human ear and “doesn’t compromise the listening experience,” and added that it should still be …

ai generated audio audio generation deepmind embedding features generated google google deepmind identify image music people synthid visual watermark watermarks youtube

Lecturer in Social Data Analytics

@ The University of Hong Kong | Hong Kong

Junior Data Scientist

@ Valerann | London, England, United Kingdom

Senior Data Lead architect (REF2159Z)

@ Deutsche Telekom IT Solutions | Budapest, Hungary

Senior Specialist - Data Management

@ Marsh McLennan | Norwich - Willow

Data Engineer – AI Applications

@ HP | TW2WA - Teleworker/Offsite-USA-WA

Senior Data Quality and Governance Analyst

@ JLL | IND-CORP Bengaluru-TDIM - PTT