CODE

Speech Synthesis

This is the official python/pytorch implementation for Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis 

If you use it please cite: 

Zaïdi, J., Seuté, H., van Niekerk, B., & Carbonneau, M.-A. (2021). Daft-Exprt: Robust Prosody Transfer Across Speakers for Expressive Speech Synthesis. http://arxiv.org/abs/2108.02271

Disentanglement Learning

We released the python code used in our experiments for Measuring Disentanglement: A Review of Metrics

If you use it please cite:

Carbonneau, M-A, Zaidi, J., Boilard, J., and Gagnon, G. (2022). Measuring disentanglement: A review of metrics. IEEE Transactions on Neural Networks and Learning Systems

Multiple Instance Learning

The Matlab code for the experiments in Multiple Instance Learning: A Survey of Problem Characteristics and Applications is available [here]. 

If you use it please cite:

Carbonneau, M. A., Cheplygina, V., Granger, E., & Gagnon, G. (2017). Multiple instance learning: A survey of problem characteristics and applications. Pattern Recognition, 77, 329–353. https://doi.org/10.1016/j.patcog.2017.10.009

Computer Vision

The Matlab code for play/break detection is now available [here] for research purposes. 

If you use it please cite:

Carbonneau, M.-A., Raymond, A. J., Granger, E., & Gagnon, G. (2015). Real-time visual play-break detection in sport events using a context descriptor. Circuits and Systems (ISCAS), 2015 IEEE International Symposium On, 2808–2811. https://doi.org/10.1109/ISCAS.2015.7169270