You are here

Speech-conditioned Face Generation using Generative Adversarial Networks

Authors: 

Amanda Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness, Jordi Torres, Xavier Giro-Nieto

Publication Type: 
Refereed Conference Meeting Proceeding
Abstract: 
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.
Conference Name: 
IEEE International Conference on Acoustics, Speech and Signal Processing
Digital Object Identifer (DOI): 
10.NA
Publication Date: 
12/05/2019
Conference Location: 
United Kingdom (excluding Northern Ireland)
Research Group: 
Institution: 
Dublin City University (DCU)
Open access repository: 
Yes