Generative personal assistance with audio and visual examples
- Deep learning opens the way to innovative media generation -
Takuhiro Kaneko, Media Information Laboratory
The rapid progress of deep learning is impacting the world we live in. Media generation (e.g., image generation and audio generation) is a typical example of this progress and many amazing research results are being reported around the world. In this talk, I will first overview this very active research field. I will then introduce our efforts regarding “generative personal assistance” with audio and visual examples. Specifically, I will explain how our new deep-learning approach will overcome the limitations of existing studies regarding personal assistance. Finally, I will discuss future directions in the media generation field.