Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore how voice assistants can be enhanced with visual capabilities in this 19-minute conference talk from DSC EUROPE 24. Darya Vinogradova presents her work on developing models that enable Yandex Alice to respond to gesture-based music control, creating more intuitive ways to interact beyond traditional voice commands. Learn about the technical process of gathering open-source data, building lightweight models, and optimizing them for specific hardware constraints. The presentation demonstrates how combining AI and computer vision technologies creates more natural and efficient user experiences, representing an important evolution in human-computer interaction. This talk was delivered on November 21st at the Data Science Conference in Belgrade.
