Deep dive on creating a photorealistic talking avatar
AI/Machine Learning • March 2022
Deep dive on creating a photorealistic talking avatar
About
Deep dive on creating a photorealistic talking avatar
About

Creating a photorealistic avatar speaking any sentence starting from a written input text.

Focusing on autoencoders, we will do a journey from the beginning (Of the speaker experience), mistakes and tips learned along the path.
Will be showcased:

  • Intro, the timeline from beginning to nowadays
  • Is NOT a deepfake
  • Audio processing techniques: STFT (Short Term Fourier Transform), MELs and custom solutions
  • Deeplearning models and architecture
  • The technique, inspired to inpaiting, used to animate the mouth
  • Masks and convolution
  • Landmarks extraction

Microsoft Azure will support us.

Language
Italian
Level
Intermediate
Length
36 minutes
Type
online conference
About the speaker
About the speaker
Sebastiano Galazzo
CTOeeve.ai
Passionate of new technologies, focused on artificial intelligence, image processing. International speaker, believing in young people, I'm committed to motivate them to embrace an manage the incoming and future technologies. Microsoft MVP for Artificial Intelligence Category, won several national and international awards. As researcher proud father of: https://www.youtube.com/watch?v=USxHjGn-e_A&t=12s. Sport man, photographer and proud dad.
Details
Language
Italian
Level
Intermediate
Length
36 minutes
Type
online conference