Anderson Ávila

Assistant Professor in the department of Energy, Materials and Telecommunications at the Institut national de la recherche scientifique (INRS) and member of the INRS-UQO Joint Research Unit in Cybersecurity.

Research interests

Federated Learning for Data Privacy

Decentralization of artificial Intelligence models by enabling efficient training and inference on edge devices to foster data privacy

Cyber Defense and Human Language Processing

Combating misinformation from a range of semantic signals, including speech, text and image

Biometrics

Improving authentication by using physical and behavioural human traits

Research Interests

Areas for present and future researchs

Training openings

Training openings for students or interns

Biography

Biography and functions of Dr. Ávila

Publications

List of works publicated by Dr. Ávila

Contact

Dr. Ávila contact information

Training openings for students or interns

Biography and Functions

Dr. Anderson Avila is an Assistant Professor at INRS-EMT, working in the INRS-UQO Joint Research Unit in Cybersecurity. His research background is on machine learning and signal processing applied to natural language processing. During his PhD, Dr. Avila worked on the development of new models for speech quality assessment and on the robustness of voice biometrics.

Prior to joining INRS-UQO, Dr. Avila was a researcher scientist in natural language and speech processing, working on projects related to model compression, low-latency and robustness of spoken language understanding.

Dr. Avila received his BSc in Computer Science from the Federal University of São Carlos, his MSc from Federal University of ABC and his PhD from INRS.

Publications

Journal

2022

H. Guimarães, A. Pimentel, A. Avila, M. Rezagholizadeh, T. Falk,

Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement, NeurIPS ENLSP Workshop, 2022.

A. Pimentel, H. Guimarães, A. Avila, M. Rezagholizadeh, T. Falk,

How Robust is Robust wav2vec 2.0 for Edge Applications?: An Exploration into the Effects of Quantization and Model Pruning on “In-the-Wild” Speech Recognition, Edge Intelligence Workshop, 2022. 

H. Guimarães, A. Pimentel, A. Avila, M. Rezagholizadeh, T. Falk,

An Exploration into the Performance of Unsupervised Cross-Task Speech Representations for ”In the Wild” Edge Applications, Edge Intelligence Workshop, 2022.

Contact

Scroll to Top