Home BIO Research Publications

Carlos Carvalho

About Me

I am a student from Instituto Superior Técnico (IST), Lisbon, doing a PhD in artificial intelligence for robust automatic speech recognition (ASR) under low-resources. Passionate about advancing Artificial Intelligence, I focus on applying cutting-edge machine learning techniques to solve complex challenges in this field. Beyond my academic pursuits, I enjoy cooking, drawing, and staying active through sports, which help me bring creativity and balance into my work. I hold an MSc from Instituto Superior Técnico, Lisbon, where I laid the foundation for my current research.

Curiosity: The background image of this website was "created" by Google DeepDream program. DeepDream was created by Google engineer Alexander Mordvintsev and was released in July 2015. You can check more here.

Contact information

carvalho.carlos21@gmail.com

Recent events

- Was a visiting student at Carnegie Mellon University - School of Computer Science - Language Technologies Institute for 3 months, working on long-form audio for speech recognition on Watanabe’s Audio and Voice (WAV) Lab (2024).
- Currently doing a PhD in creating robust automatic speech recognition (ASR) systems under low-resource scenarios. I am working at INESC-ID Lisbon, Portugal.
- Did research with speech for children at INESC-ID, Lisbon, Portugal (2020).
- In January of 2021, I finished my MSc in automatic speech recognition (ASR) by creating one of the first known state-of-the-art end-to-end systems for European Portuguese using only deep learning technology. As a result, I published a paper for IberSPEECH 2021 with the title "TRIBUS: An end-to-end automatic speech recognition system for European Portuguese" with my orientor prof. Alberto Abad.

Copyright © 2025 Carlos Carvalho.