Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks
Amanda Cardoso Duarte, Francisco Roldan, Miquel Tubau, Janna Escur, Santiago Pascual, Amaia Salvador, Eva Mohedano, Kevin McGuinness
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 approach 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 youtubers with notable expressiveness in both the speech and visual signals.
BibTeX
@inproceedings{icassp2019_wav2pixspeechcon,
title = {Wav2Pix: Speech-conditioned Face Generation Using Generative Adversarial Networks},
author = {Amanda Cardoso Duarte and Francisco Roldan and Miquel Tubau and Janna Escur and Santiago Pascual and Amaia Salvador and Eva Mohedano and Kevin McGuinness and Jordi Torres and Xavier Giró-i-Nieto},
booktitle = {ICASSP 2019},
year = {2019}
}