Eliya Nachmani

Eliya is a research assistant focusing on the intersection between machine learning information theory and signal processing. His work includes graph neural network for decoding error correcting code, speech synthesis and source separation.

Eliya's Publications

August 28, 2020

RESEARCH

A Gated Hypernet Decoder for Polar Codes

In this work, we demonstrate how hypernetworks can be applied to decode polar codes by employing a new formalization of the polar belief propagation decoding scheme.

Eliya Nachmani , Lior Wolf

August 28, 2020

August 28, 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

August 28, 2020

August 28, 2020

COMPUTER VISION

SPEECH & AUDIO

Hyper-Graph-Network Decoders for Block Codes

Neural decoders were shown to outperform classical message passing techniques for short BCH codes. In this work, we extend these results to much larger families of algebraic block codes, by performing message passing with graph neural networks.…

Eliya Nachmani, Lior Wolf

August 28, 2020

August 28, 2020

RESEARCH

SPEECH & AUDIO

Fitting New Speakers Based on a Short Untranscribed Sample

Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that is…

Eliya Nachmani, Adam Polyak, Yaniv Taigman, Lior Wolf

August 28, 2020

August 28, 2020

RESEARCH

SPEECH & AUDIO

VoiceLoop: Voice Fitting and Synthesis via a Phonolgoical Loop

We present a new neural text to speech (TTS) method that is able to transform text to speech in voices that are sampled in the wild. Unlike other systems, our solution is able to deal with unconstrained voice samples and without requiring…

Yaniv Taigman, Lior Wolf, Adam Polyak, Eliya Nachmani

August 28, 2020