Search Results for author: Tiago H. Falk

Found 14 papers, 6 papers with code

On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''

no code implementations25 Sep 2023 Arthur Pimentel, Heitor Guimarães, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk

Recent advances with self-supervised learning have allowed speech recognition systems to achieve state-of-the-art (SOTA) word error rates (WER) while requiring only a fraction of the labeled training data needed by its predecessors.

Data Augmentation Model Compression +5

Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection

1 code implementation15 Sep 2023 Yi Zhu, Saurabh Powar, Tiago H. Falk

Existing deepfake speech detection systems lack generalizability to unseen attacks (i. e., samples generated by generative algorithms not seen during training).

DeepFake Detection Face Swapping

On the Impact of Voice Anonymization on Speech-Based COVID-19 Detection

1 code implementation5 Apr 2023 Yi Zhu, Mohamed Imoussaïne-Aïkous, Carolyn Côté-Lussier, Tiago H. Falk

With advances seen in deep learning, voice-based applications are burgeoning, ranging from personal assistants, affective computing, to remote disease diagnostics.

COVID-19 Diagnosis Data Augmentation

RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness

no code implementations18 Feb 2023 Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Boxing Chen, Tiago H. Falk

The proposed layer-wise distillation recipe is evaluated on top of three well-established universal representations, as well as with three downstream tasks.

Knowledge Distillation Multi-Task Learning

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

no code implementations12 Nov 2022 Heitor R. Guimarães, Arthur Pimentel, Anderson R. Avila, Mehdi Rezagholizadeh, Tiago H. Falk

Self-supervised speech representation learning aims to extract meaningful factors from the speech signal that can later be used across different downstream tasks, such as speech and/or emotion recognition.

Data Augmentation Emotion Recognition +2

TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers

no code implementations18 Mar 2020 Karel Mundnich, Brandon M. Booth, Michelle L'Hommedieu, Tiantian Feng, Benjamin Girault, Justin L'Hommedieu, Mackenzie Wildman, Sophia Skaaden, Amrutha Nadarajan, Jennifer L. Villatte, Tiago H. Falk, Kristina Lerman, Emilio Ferrara, Shrikanth Narayanan

We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings.

Privacy Preserving

Generalizing to unseen domains via distribution matching

2 code implementations3 Nov 2019 Isabela Albuquerque, João Monteiro, Mohammad Darvishi, Tiago H. Falk, Ioannis Mitliagkas

In this work, we tackle such problem by focusing on domain generalization: a formalization where the data generating process at test time may yield samples from never-before-seen domains (distributions).

Domain Generalization LEMMA +5

Cross-Subject Statistical Shift Estimation for Generalized Electroencephalography-based Mental Workload Assessment

no code implementations20 Jun 2019 Isabela Albuquerque, João Monteiro, Olivier Rosanne, Abhishek Tiwari, Jean-François Gagnon, Tiago H. Falk

Besides shedding light on the assumptions that hold for a particular dataset, the estimates of statistical shifts obtained with the proposed approach can be used for investigating other aspects of a machine learning pipeline, such as quantitatively assessing the effectiveness of domain adaptation strategies.

Domain Adaptation EEG +1

Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation

1 code implementation23 Jan 2019 Isabela Albuquerque, João Monteiro, Tiago H. Falk

Afterwards, a recurrent model is trained with the goal of providing a sequence of inputs to the previously trained frames generator, thus yielding scenes which look natural.

Navigate Video Generation

Deep learning-based electroencephalography analysis: a systematic review

3 code implementations16 Jan 2019 Yannick Roy, Hubert Banville, Isabela Albuquerque, Alexandre Gramfort, Tiago H. Falk, Jocelyn Faubert

To help the field progress, we provide a list of recommendations for future studies and we make our summary table of DL and EEG papers available and invite the community to contribute.

Brain Decoding EEG +3

Generalizable Adversarial Examples Detection Based on Bi-model Decision Mismatch

no code implementations21 Feb 2018 João Monteiro, Isabela Albuquerque, Zahid Akhtar, Tiago H. Falk

Non-linear binary classifiers trained on top of our proposed features can achieve a high detection rate (>90%) in a set of white-box attacks and maintain such performance when tested against unseen attacks.

Cannot find the paper you are looking for? You can Submit a new open access paper.