Joao Felipe Santos

Researcher, NVIDIA

Joined

October 2018

Names

Joao Felipe Santos (Preferred)

Emails

****@emt.inrs.ca (Confirmed)

****@gmail.com (Confirmed)

****@nvidia.com (Confirmed)

Personal Links

Career & Education History

Researcher

NVIDIA (nvidia.com)

2019 – Present

PhD student

Université de Montréal (umontreal.ca)

2014 – 2019

PhD student

Institut national de la recherche scientifique (inrs.ca)

2013 – 2019

MS student

Institut national de la recherche scientifique (inrs.ca)

2012 – 2013

Undergrad student

Universidade Federal de Santa Catarina (ufsc.br)

2005 – 2010

Advisors, Relations & Conflicts

Coauthor

Yoshua Bengio

2014 – Present

PhD Advisor

Tiago H. Falk

2012 – 2019

Expertise

Speech synthesis

2016 – Present

Speech enhancement

2014 – Present

Publications

Music Flamingo: Scaling Music Understanding in Audio Language Models
Sreyan Ghosh, Arushi Goel, Lasha Koroshinadze, Sang-gil Lee, Zhifeng Kong, Joao Felipe Santos, Ramani Duraiswami, Dinesh Manocha, Wei Ping, Mohammad Shoeybi, Bryan Catanzaro
- ICLR 2026 Poster
- Readers: Everyone
Audio-to-Audio Schrodinger Bridges
Kevin J. Shih, Zhifeng Kong, Weili Nie, Arash Vahdat, Sang-gil Lee, Joao Felipe Santos, Ante Jukić, Rafael Valle, Bryan Catanzaro
- AI4Music
- Readers: Everyone
A$^2$-Flow: Alignment-Aware Pre-training for Speech Synthesis with Flow Matching
Sungwon Kim, Sang-gil Lee, Alexander H. Liu, Joao Felipe Santos, Mikyas T. Desta, Sudheer Kovela, Rafael Valle, Bryan Catanzaro
- Submitted to ICLR 2025
- Readers: Everyone
Fugatto 1: Foundational Generative Audio Transformer Opus 1
Rafael Valle, Rohan Badlani, Zhifeng Kong, Sang-gil Lee, Arushi Goel, Sungwon Kim, Joao Felipe Santos, Shuqi Dai, Siddharth Gururani, Aya Aljafari, Alexander H. Liu, Kevin J. Shih, Ryan Prenger, Wei Ping, Chao-Han Huck Yang, Bryan Catanzaro
- ICLR 2025 Poster
- Readers: Everyone
P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting
Sungwon Kim, Kevin J. Shih, Rohan Badlani, Joao Felipe Santos, Evelina Bakhturina, Mikyas T. Desta, Rafael Valle, Sungroh Yoon, Bryan Catanzaro
- NeurIPS 2023 poster
- Readers: Everyone
Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flows
Kevin J. Shih, Rafael Valle, Rohan Badlani, João Felipe Santos, Bryan Catanzaro
- 2022 (modified: 22 Apr 2022)
- CoRR 2022
- Readers: Everyone
Feature Pooling of Modulation Spectrum Features for Improved Speech Emotion Recognition in the Wild
Anderson R. Avila, Zahid Akhtar, João Felipe Santos, Douglas D. O'Shaughnessy, Tiago H. Falk
- 2021 (modified: 22 Apr 2022)
- IEEE Trans. Affect. Comput. 2021
- Readers: Everyone
Non-Intrusive Speech Quality Prediction Using Modulation Energies and LSTM-Network
Benjamin Cauchi, Kai Siedenburg, João Felipe Santos, Tiago H. Falk, Simon Doclo, Stefan Goetze
- 2019 (modified: 22 Apr 2022)
- IEEE ACM Trans. Audio Speech Lang. Process. 2019
- Readers: Everyone
Representation Mixing for TTS Synthesis
Kyle Kastner, João Felipe Santos, Yoshua Bengio, Aaron C. Courville
- 2019 (modified: 22 Apr 2022)
- ICASSP 2019
- Readers: Everyone
Towards the development of a non-intrusive objective quality measure for DNN-enhanced speech
João Felipe Santos, Tiago H. Falk
- 2019 (modified: 22 Apr 2022)
- QoMEX 2019
- Readers: Everyone

View all 33 publications

Co-Authors

View all 82 co-authors