Sign up for email alert when new content gets added: Sign up
Sebastiano Galazzo
Sistem-evo, Italy
Keynote: Nanotechnol Lett
Creating a photorealistic avatar speaking any sentence starting from a written input text. Focusing on auto encoders, we will do a journey from the beginning (Of the speaker experience), mistakes and tips learned along the path. Let’s take a look at what will be showcased in this talk. Firstly intro, the timeline from beginning to nowadays, is NOT a deep fake, audio processing techniques: STFT (Short Term Fourier Transform), MELs and custom solutions, deep learning models and architecture, the technique, inspired to inpaiting, used to animate the mouth, masks and convolution, landmarks extraction, morphing animation technique based on auto encoders features, Microsoft Azure Speech services used to support audio and animation processing, and finally putting all together.
Recent Publications:
1) Sebastiano Galazzo. Windows Phone: HDR I - Implementing High Dynamic Range filters using Nokia Imaging SDK
2) Sebastiano Galazzo. Windows Phone: Neural Network based Image Processing
3) Sebastiano Galazzo. Windows Phone: Face Recognition using 2D Fast Fourier Transform.
Sebastiano Galazzo is an artificial intelligence researcher. He is the winner of two AI awards and has been working in AI and machine learning for 20 years, designing and developing AI and computer graphic algorithms. He is very passionate about AI, interested in technologies focused on image and natural language processing, and predictive analysis. He received several national and international awards that recognize his work and contributions in these areas.
