A deep learning audiovisual model from Google could impact voice-search, retail and creative production.
Announced on the Research Blog, the method can, according to Google, identify audio found in a video by isolating spoken words and distinguishing between language in the foreground and background.
- Campaign Asia-Pacific online premium content* including in-depth monthly focus on key trends and industry issues
- Unlimited website access*, and an archive of more than 70,000 articles
- Regular value-added supplements including brand health checks, sector studies, ad critiques and research charts
- Daily newsletters and breaking story alerts straight to your inbox
- New weekly feature articles on the latest research, innovation and marketing trends
- Be the first to hear about industry events