Deep learning

Never Too Many Neurons in Speech Recognition

The field of speech recognition has been the talk of the town for decades and now has numerous applications, from automatic captioning to callbots. And its revolution continues today, with the exploration of end-to-end neural approaches.

Read the article
A woman talks to her smartphone

Generative AI: a new approach to overcome data scarcity

Read the article
A man having his face scanned by a tablet for better audiovisual recognition

Better Hearing Through Seeing: Separating Voices in an Audiovisual Stream

Read the article

Encrypting or classifying Internet traffic: do we have to choose?

Read the article

Video Compression: A Neural Network Challenging the Conventional Approach

Read the article

Self-supervised learning paves the way for a common-sense AI

Read the article