Lior Wolf

Lior is a Research Scientist at the Facebook AI Research (FAIR) Group. He is also a Full Professor at the School of Computer Science at Tel Aviv University. Prior to that, Lior was a post-doctoral associate at MIT and graduated from the Hebrew University in Jerusalem. He is an ERC grantee and won the Best Paper awards at ECCV 2000, the post ICCV 2009 workshop on eHeritage, the pre-CVPR2013 workshop on action recognition, and ICANN 2016. He also received the ICCV 2001 Marr Prize honorable mention, and the ICCV 2019 honorable mention. Lior's research focuses on computer vision and deep learning, and includes topics such as face identification, speech and audio synthesis, digital paleography, and video action recognition.

Lior's Publications

April 07, 2020

RESEARCH

COMPUTER VISION

Live Face De-Identification in Video

We propose a method for face de-identification that enables fully automatic video modification at high frame rates. The goal is to maximally decorrelate the identity, while having the perception (pose, illumination and expression) fixed. We…

Oran Gafni, Lior Wolf, Yaniv Taigman,

April 07, 2020

April 07, 2020

RESEARCH

NLP

Unsupervised Singing Voice Conversion

We present a deep learning method for singing voice conversion. The proposed network is not conditioned on the text or on the notes, and it directly converts the audio of one singer to the voice of another. Training is performed without any…

Eliya Nachmani, Lior Wolf,

April 07, 2020

April 07, 2020

RESEARCH

SPEECH & AUDIO

A Universal Music Translation Network

We present a method for translating music across musical instruments and styles. This method is based on unsupervised training of a multi-domain wavenet autoencoder, with a shared encoder and a domain-independent latent space that is trained…

Noam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman,

April 07, 2020