Sorry, you need to enable JavaScript to visit this website.

Wav2Pix: Speech-conditioned Face Generation using Generative Adversarial Networks

Citation Author(s):
Amanda Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giro-i-Nieto
Submitted by:
Xavier Giro
Last updated:
10 May 2019 - 1:12pm
Document Type:
Presentation Slides
Document Year:
2019
Event:
Presenters:
Xavier Giro-i-Nieto
Paper Code:
ICASSP19005
Categories:
 

Speech is a rich biometric signal that contains information about the identity, gender and emotional state of the speaker. In this work, we explore its potential to generate face images of a speaker by conditioning a Generative Adversarial Network (GAN) with raw speech input. We propose a deep neural network that is trained from scratch in an end-to-end fashion, generating a face directly from the raw speech waveform without any additional identity information (e.g reference image or one-hot encoding). Our model is trained in a self-supervised fashion by exploiting the audio and visual signals naturally aligned in videos. With the purpose of training from video data, we present a novel dataset collected for this work, with high-quality videos of ten youtubers with notable expressiveness in both the speech and visual signals.

up
0 users have voted: