Search Results for author: Marc-André Carbonneau

Found 8 papers, 6 papers with code

Rhythm Modeling for Voice Conversion

1 code implementation12 Jul 2023 Benjamin van Niekerk, Marc-André Carbonneau, Herman Kamper

Voice conversion aims to transform source speech into a different target voice.

Voice Conversion

ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech

1 code implementation15 Sep 2022 Saeed Ghorbani, Ylva Ferstl, Daniel Holden, Nikolaus F. Troje, Marc-André Carbonneau

In a series of experiments, we first demonstrate the flexibility and generalizability of our model to new speakers and styles.

Gesture Generation

Energy Disaggregation using Variational Autoencoders

1 code implementation22 Mar 2021 Antoine Langevin, Marc-André Carbonneau, Mohamed Cheriet, Ghyslain Gagnon

In this paper we address these issues and propose an energy disaggregation approach based on the variational autoencoders framework.

Non-Intrusive Load Monitoring

Measuring Disentanglement: A Review of Metrics

1 code implementation16 Dec 2020 Marc-André Carbonneau, Julian Zaidi, Jonathan Boilard, Ghyslain Gagnon

While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement.


Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Problems

no code implementations6 Oct 2017 Marc-André Carbonneau, Eric Granger, Ghyslain Gagnon

In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances.

Active Learning General Classification +2

Multiple Instance Learning: A Survey of Problem Characteristics and Applications

1 code implementation11 Dec 2016 Marc-André Carbonneau, Veronika Cheplygina, Eric Granger, Ghyslain Gagnon

Multiple instance learning (MIL) is a form of weakly supervised learning where training instances are arranged in sets, called bags, and a label is provided for the entire bag.

Benchmarking Document Classification +2

Feature Learning from Spectrograms for Assessment of Personality Traits

no code implementations4 Oct 2016 Marc-André Carbonneau, Eric Granger, Yazid Attabi, Ghyslain Gagnon

The number of features, and difficulties linked to the feature extraction process are greatly reduced as only one type of descriptors is used, for which the 6 parameters can be tuned automatically.

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