Tal Remez Ph.D

talremez at gmail dot com

visually driven tts I am part of Google Research and Machine Intelligence (RMI). Before that I was an intern at Google, General Motors and Microsoft. I received my PhD and MSc from Tel-Aviv University, where I was advised by Prof. Alex Bronstein and Prof. Shai Avidan. I recieved my MBA and BSc in Applied Physics from the Hebrew University under Amirim.

My research interests include: visual perception and computational photography as well as audio-visual applications for speech and audio enhancement.

I’m searching for my next big challenge where I can make a significant impact.





Publications

visually driven tts

More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech

Michael Hassid, Michelle Tadmor Ramanovich, Brendan Shillingford, Miaosen Wang, Ye Jia, Tal Remez

Under review CVPR 2022




Improving On-Screen Sound Separation for Open Domain Videos with Audio-Visual Self-attention

Improving On-Screen Sound Separation for Open Domain Videos with Audio-Visual Self-attention

Efthymios Tzinis, Scott Wisdom, Tal Remez, John R Hershey

Under review CVPR 2022




Translatotron 2: Robust direct speech-to-speech translation

Translatotron 2: Robust direct speech-to-speech translation

Ye Jia, Michelle Tadmor Ramanovich, Tal Remez, Roi Pomerantz

Under review ICLR 2022

Website




Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds

Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds

Efthymios Tzinis, Scott Wisdom, Aren Jansen, Shawn Hershey, Tal Remez, Daniel P. W. Ellis, John R. Hershey

ICLR 2021




Learning to Segment via Cut-and-Paste

Learning to Segment via Cut-and-Paste

Tal Remez, Jonathan Huang, Matthew Brown

ECCV 2018




Class-Aware Fully-Convolutional Gaussian and Poisson Denoising

Class-Aware Fully-Convolutional Gaussian and Poisson Denoising

Tal Remez, Or Litany, Raja Giryes, Alex M. Bronstein

TIP 2018




Deep Functional Maps: Structured Prediction for Dense Shape Correspondence

Deep Functional Maps: Structured Prediction for Dense Shape Correspondence

Or Litany, Tal Remez, Emanuele Rodolà, Alex M. Bronstein, Michael M. Bronstein

ICCV 2017




Deep Class Aware Image Denoising

Deep Class Aware Image Denoising

Tal Remez, Or Litany, Raja Giryes and Alex M. Bronstein

ICIP 2017

GitHub





Deep Convolutional Denoising of Low-Light Images

Deep Convolutional Denoising of Low-Light Images

Tal Remez, Or Litany, Raja Giryes and Alex M. Bronstein




Cloud Dictionary: Sparse Coding and Modeling for Point Clouds

Cloud Dictionary: Sparse Coding and Modeling for Point Clouds

Or Litany*, Tal Remez*, Alex Bronstein

SPARS 2017




ASIST: Automatic Semantically Invariant Scene Transformation

ASIST: Automatic Semantically Invariant Scene Transformation

Or Litany, Tal Remez, Daniel Freedman, Lior Shapira, Alex Bronstein, Ran Gal

CVIU 2017




A picture is worth a billion bits: Real-time image reconstruction from dense binary threshold pixels

A picture is worth a billion bits: Real-time image reconstruction from dense binary threshold pixels

Tal Remez,Or Litany, Alex Bronstein

ICCP 2016 Oral




Image reconstruction from dense binary pixels

Image reconstruction from dense binary pixels

Or Litany*, Tal Remez*, Alex Bronstein

SPARS 2015