Zalán Borsos

Zalán Borsos

I am a staff research scientist at Google DeepMind working on generative models for audio. Before this, I was a PhD student at ETH Zurich under the supervision of Prof. Andreas Krause. My PhD research focused on data summarization and adaptive data subsampling techniques for resource-constrained machine learning systems.

Selected Publications

SoundStorm: Efficient Parallel Audio Generation
Zalán Borsos, Matt Sharifi, Damien Vincent, Eugene Kharitonov, Neil Zeghidour, Marco Tagliasacchi
arXiv:2305.09636, 2023
[paper] [blog post]

Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision
Eugene Kharitonov, Damien Vincent, Zalán Borsos, Raphaël Marinier, Sertan Girgin, Olivier Pietquin, Matt Sharifi, Marco Tagliasacchi, Neil Zeghidour
arXiv:2302.03540, 2023
[paper]

MusicLM: Generating Music From Text
Andrea Agostinelli, Timo I. Denk, Zalán Borsos, Jesse Engel, Mauro Verzetti, Antoine Caillon, Qingqing Huang, Aren Jansen, Adam Roberts, Marco Tagliasacchi, Matt Sharifi, Neil Zeghidour, Christian Frank
arXiv:2301.11325, 2023
[paper]

AudioLM: a Language Modeling Approach to Audio Generation
Zalán Borsos, Raphaël Marinier, Damien Vincent, Eugene Kharitonov, Olivier Pietquin, Matt Sharifi, Olivier Teboul, David Grangier, Marco Tagliasacchi, Neil Zeghidour
TASLP, 2023
[paper] [blog post]

SpeechPainter: Text-conditioned Speech Inpainting
Zalán Borsos, Matt Sharifi, Marco Tagliasacchi
INTERSPEECH, 2022
[paper]

Data Summarization via Bilevel Optimization
Zalán Borsos, Mojmír Mutńy, Marco Tagliasacchi, Andreas Krause
arXiv:2109.12534, 2021
[paper]

MicAugment: One-shot Microphone Style Transfer
Zalán Borsos, Yunpeng Li, Beat Gfeller, Marco Tagliasacchi
International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021
[paper]

Coresets via Bilevel Optimization for Continual Learning and Streaming
Zalán Borsos, Mojmír Mutný, Andreas Krause
Neural Information Processing Systems (NeurIPS), 2020
[paper] [code]

Online Variance Reduction with Mixtures
Zalán Borsos, Sebastian Curi, Kfir Yehuda Levy, Andreas Krause
International Conference on Machine Learning (ICML), 2019
[paper] [code]

Online Variance Reduction for Stochastic Optimization
Zalán Borsos, Andreas Krause, Kfir Yehuda Levy
Conference On Learning Theory (COLT), 2018
[paper] [code]

Implementing Modular FFTs in FPGAs–A Basic Block for Lattice-Based Cryptography
Tamas Györfi, Octavian Cret, Zalán Borsos
Digital System Design (DSD), 2013
[paper]