Luis C. Cobo

Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.

? Tutorial for this page

Demo Data from EDBT 2026 / reviewers in the wild / expert

dblp:96/9924 · DBLP profile ↗

← Back

5ranked-venue papers

2as first author

0since 2021 · last 2020

—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 5 · 2 first-authorGraphics, computer vision, multimedia, augmented reality and games · 1 · 1 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence

5 papers

Speech recognition and synthesis · 56% Reinforcement learning · 16% Generative modeling · 14%

Topics — the 10 heaviest of 11, each with the papers that count most for it

Topic	Weight	Papers	Last	Evidence papers
Natural language and speech › Speech recognition and synthesis speech synthesis	0.8	2	2020	High Fidelity Speech Synthesis with Adversarial Networks · ICLR 2020 Parallel WaveNet: Fast High-Fidelity Speech Synthesis · ICML 2018
Machine learning › Generative modeling generative adversarial network	0.4	1	2020	High Fidelity Speech Synthesis with Adversarial Networks · ICLR 2020
Natural language and speech › Speech recognition and synthesis › speech synthesis text-to-speech	0.4	1	2019	Sample Efficient Adaptive Text-to-Speech · ICLR (Poster) 2019
Machine learning › Efficient and distributed learning › model compression knowledge distillation	0.3	1	2018	Parallel WaveNet: Fast High-Fidelity Speech Synthesis · ICML 2018
Natural language and speech › Speech recognition and synthesis › speech synthesis neural speech synthesis	0.3	1	2018	Parallel WaveNet: Fast High-Fidelity Speech Synthesis · ICML 2018
Natural language and speech › Speech recognition and synthesis › speech synthesis › neural speech synthesis parallel speech synthesis	0.3	1	2018	Parallel WaveNet: Fast High-Fidelity Speech Synthesis · ICML 2018
Machine learning › Reinforcement learning efficient reinforcement learning	0.2	1	2014	Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains · Artif. Intell. 2014
Machine learning › Reinforcement learning › function approximation › representation learning for reinforcement learning state abstraction	0.1	1	2011	Automatic State Abstraction from Demonstration · IJCAI 2011
Machine learning › Efficient and distributed learning inference acceleration	0.1	1	2018	Parallel WaveNet: Fast High-Fidelity Speech Synthesis · ICML 2018
Robotics › Robot manipulation learning from demonstration	0.0	1	2011	Automatic State Abstraction from Demonstration · IJCAI 2011

Methods — techniques the papers use, named apart from their topics

adversarial network · 0.4meta-learning · 0.4probability density distillation · 0.3autoregressive modeling · 0.3reinforcement learning · 0.2demonstration · 0.2abstraction · 0.2state abstraction · 0.1learning from demonstration · 0.1

Year	Publication	Venue	Position
2020	High Fidelity Speech Synthesis with Adversarial Networks Mikolaj Binkowski, Jeff Donahue, Sander Dieleman, Aidan Clark, Erich Elsen, Norman Casagrande, Luis C. Cobo, Karen Simonyan	ICLR	7
2019	Sample Efficient Adaptive Text-to-Speech Yutian Chen 0001, Yannis M. Assael, Brendan Shillingford, David Budden, Scott E. Reed, Heiga Zen, Luis C. Cobo, Andrew Trask, Ben Laurie, Caglar Gulcehre, Aäron van den Oord, Oriol Vinyals, Nando de Freitas	ICLR (Poster)	8
2018	Parallel WaveNet: Fast High-Fidelity Speech Synthesis abstract The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today’s massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. The resulting system is capable of generating high-fidelity speech samples at more than 20 times faster than real-time, a 1000x speed up relative to the original WaveNet, and capable of serving multiple English and Japanese voices in a production setting. Aäron van den Oord, Yazhe Li, Igor Babuschkin, Karen Simonyan, Oriol Vinyals, Koray Kavukcuoglu, George van den Driessche 0002, Edward Lockhart, Luis C. Cobo, Florian Stimberg, Norman Casagrande, Dominik Grewe, Seb Noury, Sander Dieleman, Erich Elsen, Nal Kalchbrenner, Heiga Zen, Alex Graves, Helen King, Tom Walters, Daniel Belov, Demis Hassabis	ICML	9
2014	Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains Luis C. Cobo, Kaushik Subramanian, Charles L. Isbell Jr., Aaron D. Lanterman, Andrea Thomaz	Artif. Intell.	1
2011	Automatic State Abstraction from Demonstration Luis C. Cobo, Peng Zang, Charles L. Isbell Jr., Andrea Thomaz	IJCAI	1