Francisco Teixeira
From HLT@INESC-ID
Francisco Teixeira received the Integrated M.Sc. in Electrical and Computer Engineering degree from Instituto Superior Técnico (IST), University of Lisbon, in 2018 and his Ph.D. degree from the same institution in 2024. He was a member of the International Speech Communication Association - Student Advisory Committee (ISCA-SAC) from 2020-2024. He was a part of the PrivaDia project, and is currently a postdoc researcher at the Human Language Technologies Lab (HLT) at INESC-ID, under the Accelerat.AI project. His main research interests is privacy-preserving machine learning with a main focus on speech processing. In particular, his research focuses on cryptographic and machine learning methods for privacy in remote speech processing settings, as well as methods to evaluate the privacy of the training data of speech-based machine learning models.
Research interests: Speech Processing, Machine Learning, Privacy, Cryptography
Total Publications: 22
Article (Author)
- Privacy-oriented manipulation of speaker representations
Francisco Teixeira, Alberto Abad, Bhiksha Raj, Isabel Trancoso,
IEEE Access, vol. 12, pages 82949-82971, DOI 10.1109/ACCESS.2024.3409067, June 2024 - Preserving Privacy in Speaker and Speech Characterisation
Andreas Nautsch, Abelino Jiménez, Amos Treiber, Jascha Kolberg, Catherine Jasserand, Els Kindt, Héctor Delgado, Massimiliano Todisco, Mohamed Amine Hmani, Aymen Mtibaa, Mohammed Ahmed Abdelraheem, Alberto Abad, Francisco Teixeira, Driss Matrouf, Marta Gomez-Barrero, Dijana Petrovska-Delacretaz, Gerard Chollet, Nicholas Evans, Thomas Schneider, Jean-François Bonastre, Bhiksha Raj, Isabel Trancoso, Christoph Busch,
Computer Speech & Language, vol. 58, pages 441--480, DOI https://doi.org/10.1016/j.csl.2019.06.001, November 2019
In Proceedings (Author)
- Privacy-preserving Machine Learning for Remote Speech Processing
Francisco Teixeira, Alberto Abad, Bhiksha Raj, Isabel Trancoso,
Proceedings IberSpeech 2024, pages 246-250, International Speech Communication Association (ISCA), November 2024 - Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
Francisco Teixeira, Karla Pizzi, Raphael Olivier, Alberto Abad, Bhiksha Raj, Isabel Trancoso,
Trustworthy Speech Processing (TSP) Workshop, Satellite Workshop, International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 2024 - Privacy-preserving Automatic Speaker Diarization
Francisco Teixeira, Alberto Abad, Bhiksha Raj, Isabel Trancoso,
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pages 1-5, IEEE, June 2023 - Towards End-to-End Private Automatic Speaker Recognition
Francisco Teixeira, Alberto Abad, Bhiksha Raj, Isabel Trancoso,
Proc. Interspeech 2022, pages 2798-2802, September 2022 - Transfer Learning-Based Cough Representations for Automatic Detection of COVID-19
Rubén Solera Ureña, Catarina Botelho, Francisco Teixeira, Thomas Rolland, Alberto Abad, Isabel Trancoso,
Interspeech 2021, pages 436--440, International Speech Communication Association, August 2021 - The in-the-Wild Speech Medical Corpus
Maria Joana Ribeiro Folgado Correia, Francisco Teixeira, Catarina Botelho, Isabel Trancoso, Bhiksha Raj,
ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, pages 6973-6977, IEEE, June 2021 - FoolHD: Fooling Speaker Identification by Highly Imperceptible Adversarial Disturbances
Ali Shahin Shamsabadi, Francisco Teixeira, Alberto Abad, Bhiksha Raj, Andrea Cavallaro, Isabel Trancoso,
ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, pages 6159-6163, IEEE, June 2021 - Analyzing Breath Signals for the Interspeech 2020 ComParE Challenge
John Mendonça, Francisco Teixeira, Isabel Trancoso, Alberto Abad,
Interspeech 2020, October 2020 - Profiling speech for clinical applications
Isabel Trancoso, Francisco Teixeira, Maria Joana Ribeiro Folgado Correia, Catarina Botelho, Alberto Abad, Bhiksha Raj,
(Keynote paper) SPECOM - 22nd International Conference on Speech and Computer, St. Petersburg, Russia, October 2020 - Speech – a health biomarker
Isabel Trancoso, Maria Joana Ribeiro Folgado Correia, Francisco Teixeira, Catarina Botelho, Alberto Abad, Bhiksha Raj,
(Keynote paper) International Conference on Computational Processing of the Portuguese Language, LNCS and LNAI, Springer, vol. 12037, Springer, Évora, Portugal, March 2020 - Speech as a (private?) biomarker for speech affecting diseases
Isabel Trancoso, Maria Joana Ribeiro Folgado Correia, Francisco Teixeira, Alberto Abad, Catarina Botelho, Bhiksha Raj,
(Keynote) ICIEA 2019 - The 14th IEEE Conference on Industrial Electronics and Applications, IEEE, IEEE, Xi'an, China, June 2019 - Privacy-Preserving Paralinguistic Tasks
Francisco Teixeira, Alberto Abad, Isabel Trancoso,
ICASSP 2019, IEEE, pages 6575--6579, IEEE, Brighton, UK, May 2019 - Analysing Speech for Clinical Applications
Isabel Trancoso, Maria Joana Ribeiro Folgado Correia, Francisco Teixeira, Alberto Abad,
(keynote paper) T. Dutoit et al. (Eds.): SLSP 2018, Lecture Notes in Artificial Intelligence, Springer, vol. 11171, pages 3--6, Springer, October 2018 - Patient Privacy in Paralinguistic Tasks
Francisco Teixeira, Alberto Abad, Isabel Trancoso,
Interspeech 2018, ISCA, pages 3428--3432, ISCA, Hyderabad, India, September 2018 - Mining multimodal repositories for speech affecting diseases
Maria Joana Ribeiro Folgado Correia, Bhiksha Raj, Isabel Trancoso, Francisco Teixeira,
Interspeech 2018, ISCA, pages 2963--2967, ISCA, Hyderabad, India, September 2018 - Speech Analytics for Medical Applications.
Isabel Trancoso, Maria Joana Ribeiro Folgado Correia, Francisco Teixeira, Bhiksha Raj, Alberto Abad,
(keynote paper) Text, Speech, and Dialogue - TSD 2018, Sojka P., Horák A., Kopeček I., Pala K. (eds), Lecture Notes in Computer Science, Springer, Cham, vol. 11107, pages 26--37, Springer, Cham, September 2018
In Book (Author)
- Privacy in Paralinguistic and Extralinguistic Tasks for Health Applications
Francisco Teixeira, Alberto Abad, Isabel Trancoso, Bhiksha Raj,
Voice Biometrics: Technology, Trust and Security, The Institution of Engineering and Technology (IET), October 2021
Thesis (Author)
- Privacy-preserving Machine Learning for Remote Speech Processing
Francisco Teixeira, Departamento de Engenharia Electrotécnica e de Computadores, Instituto Superior Técnico, Universidade de Lisboa, Thesis, July 2024 - Privacy in Paralinguistic Tasks
Francisco Teixeira, Instituto Superior Técnico, Universidade de Lisboa, Thesis, September 2018
Total Projects: 2
National Projects
- ACCELERAT.AI - ACCELERAT.AI
DEFINED AI, IAPMEI, Societal Digital Transformation, Instituto Superior Técnico, Universidade de Lisboa, FFCUL, NOS Comunicações, Devscope - Soluções De Sistemas E Tecnologias De Formação, S.A., INESC-ID Lisboa, FCiências.ID - Associação para a Investigação e Desenvolvimento de Ciências2023-01-01 - 2025-12-21 - PRIVADIA - Privacidade em diarização do orador: deteção segura de - quem fala quando
INESC-ID Lisboa, FCT, Security and Privacy, 2021-01-01 - 2022-06-30