DevDays Europe 2022

Sebastiano Galazzo

Position: CTO

Company: eeve.ai

Country: Italy

Biography

Winner of two AI awards, He has been working in AI and machine learning for 20 years, designing and developing AI and computer graphic algorithms. Very passionate about AI, interested in technologies focused on Image and Natural Language Processing as well computer vision. He received several national and international awards, that recognize his work and contributions in these areas. Microsoft MVP for Artificial Intelligence Category, international speaker, but first of all, proud dad.

Talk

Deep Dive on Creating a Photorealistic Talking Avatar

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
– Deep learning models and architecture
– The technique, inspired to inpainting, used to animate the mouth
– Masks and convolution
– Landmarks extraction
– Morphing animation technique based on autoencoders features
– Microsoft Azure Speech services used to support audio and animation processing
– Putting all together

Session Keywords

🔑 Deep Learning
🔑 Computer Vision
🔑 Audio processing
🔑 Avatars

« Back