Publications

Multi-Task Self-Supervised Learning for Robust Speech Recognition
Mirco Ravanelli
Jianyuan Zhong
Santiago Pascual
Pawel Swietojanski
Joao Monteiro
Jan Trmal
Yoshua Bengio
Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To t… (see more)ake a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation. Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.
2020-05-03
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)
doi.org
arxiv.org
Suitable e-Health Solutions for Older Adults with Dementia or Mild Cognitive Impairment: Perceptions of Health and Social Care Providers in Quebec City
Marie-Pierre Gagnon
Mame Ndiaye
Mylène Boucher
Samantha Dequanter
Ronald Buyl
Ellen Gorus
Anne Bourbonnais
Anik Giguère
S. A. Rahimi
: e-Health solutions offer a potential to improve the quality of life and safety of older adults with dementia or mild cognitive impairment … (see more)(MCI). In making better decisions for using eHealth technologies, health professionals should be aware and well informed about existing tools. Recent research shows the lack of knowledge on these technologies for older adults with dementia. In Quebec, current market offer for these technologies is supply-based, and not need-based. This study is part of a larger project and aims to understand the perceptions and needs of health and social care providers regarding e-health technologies for older adults with dementia or MCI. One focus group was carried out with six health and social care professionals at the St-Sacrement Hospital in Quebec City, Canada. The focus group enquired about the use of Information and Communication Technology (ICT) with older adults with cognitive impairment. Relevant examples of ICTs were presented to assess their knowledge level. The discussion was tape-recorded and transcripts were coded using the Nvivo software. Results revealed that aside from fall safety technologies, there is a lack of knowledge about other e-Health technologies for this population. Respondents acknowledged the value of ICTs and were willing to recommend some of them. Economic reasons, blind trust on ICTs and lack of confidence in patients’ capacity to use the solutions were the major limitations identified.
2020-05-02
Proceedings of the 6th International Conference on Information and Communication Technologies for Ageing Well and e-Health (published)
doi.org
General Principles of Gene Dosage Effects on Brain Structure
Claudia Modenato
Kuldeep Kumar
Clara A. Moreau
Catherine Schramm
Guillaume Huguet
Sandra Martin-Brevet
Aurélie Pain
Anne M. Maillard
Sonia Richetin
Borja Rodriguez-Herreros
Lester Melie-Garcia
Ana Dos Santos Silva
Marianne B.M. van den Bree
David E.J. Linden
Carrie E. Bearden
Danilo Bzdok
Sarah Lippé
Mallar Chakravarty
Bogdan Draganski
Sébastien Jacquemont
2020-04-30
Biological Psychiatry (published)
doi.org
HipoRank: Incorporating Hierarchical and Positional Information into Graph-based Unsupervised Long Document Extractive Summarization
Yue Dong
Andrei Mircea
Jackie CK Cheung
We propose a novel graph-based ranking model for unsupervised extractive summarization of long documents. Graph-based ranking models typical… (see more)ly represent documents as undirected fully-connected graphs, where a node is a sentence, an edge is weighted based on sentence-pair similarity, and sentence importance is measured via node centrality. Our method leverages positional and hierarchical information grounded in discourse structure to augment a document's graph representation with hierarchy and directionality. Experimental results on PubMed and arXiv datasets show that our approach outperforms strong unsupervised baselines by wide margins and performs comparably to some of the state-of-the-art supervised models that are trained on hundreds of thousands of examples. In addition, we find that our method provides comparable improvements with various distributional sentence representations; including BERT and RoBERTa models fine-tuned on sentence similarity.
2020-04-30
ArXiv (preprint)
arxiv.org
arxiv.org
Route choice behaviour and travel information in a congested network: Static and dynamic recursive models
G. M. Ramos
Tien Mai
W. Daamen
Emma Frejinger
S. Hoogendoorn
2020-04-30
Transportation Research Part C: Emerging Technologies (published)
doi.org
Systems consolidation impairs behavioral flexibility
Sankirthana Sathiyakumar
Sofia Skromne Carrasco
Lydia Saad
Blake Aaron Richards
2020-04-30
Learning & Memory (published)
doi.org
What Can Machine Learning Do for Psychiatry?
Daniel S. Barron
Danilo Bzdok
John H. Krystal
R. Todd Constable
2020-04-30
Biological Psychiatry (published)
doi.org
Autism spectrum heterogeneity: fact or artifact?
Laurent Mottron
Danilo Bzdok
2020-04-29
Molecular Psychiatry (published)
doi.org
Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation
Maxence Ernoult
Julie Grollier
Damien Querlioz
Yoshua Bengio
Benjamin Scellier
Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. It appli… (see more)es to RNNs fed by a static input x that settle to a steady state, such as Hopfield networks. EP is similar to BP in that in the second phase of training, an error signal propagates backwards in the layers of the network, but contrary to BP, the learning rule of EP is spatially local. Nonetheless, EP suffers from two major limitations. On the one hand, due to its formulation in terms of real-time dynamics, EP entails long simulation times, which limits its applicability to practical tasks. On the other hand, the biological plausibility of EP is limited by the fact that its learning rule is not local in time: the synapse update is performed after the dynamics of the second phase have converged and requires information of the first phase that is no longer available physically. Our work addresses these two issues and aims at widening the spectrum of EP from standard machine learning models to more bio-realistic neural networks. First, we propose a discrete-time formulation of EP which enables to simplify equations, speed up training and extend EP to CNNs. Our CNN model achieves the best performance ever reported on MNIST with EP. Using the same discrete-time formulation, we introduce Continual Equilibrium Propagation (C-EP): the weights of the network are adjusted continually in the second phase of training using local information in space and time. We show that in the limit of slow changes of synaptic strengths and small nudging, C-EP is equivalent to BPTT (Theorem 1). We numerically demonstrate Theorem 1 and C-EP training on MNIST and generalize it to the bio-realistic situation of a neural network with asymmetric connections between neurons.
2020-04-28
ArXiv (preprint)
arxiv.org
arxiv.org
Equilibrium Propagation with Continual Weight Updates
Maxence Ernoult
Julie Grollier
Damien Querlioz
Yoshua Bengio
Benjamin Scellier
Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching… (see more) those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input
2020-04-28
arXiv (preprint)
doi.org
openreview.net
ArguLens: Anatomy of Community Opinions On Usability Issues Using Argumentation Models
Wenting Wang
Deeksha M. Arya
Nicole Novielli
Jinghui Cheng
Jin L.C. Guo
In open-source software (OSS), the design of usability is often influenced by the discussions among community members on platforms such as i… (see more)ssue tracking systems (ITSs). However, digesting the rich information embedded in issue discussions can be a major challenge due to the vast number and diversity of the comments. We propose and evaluate ArguLens, a conceptual framework and automated technique leveraging an argumentation model to support effective understanding and consolidation of community opinions in ITSs. Through content analysis, we anatomized highly discussed usability issues from a large, active OSS project, into their argumentation components and standpoints. We then experimented with supervised machine learning techniques for automated argument extraction. Finally, through a study with experienced ITS users, we show that the information provided by ArguLens supported the digestion of usability-related opinions and facilitated the review of lengthy issues. ArguLens provides the direction of designing valuable tools for high-level reasoning and effective discussion about usability.
2020-04-22
Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems (published)
doi.org
arxiv.org
Inference for travel time on transportation networks
Mohamad Elmasri
Aurélie Labbe
Denis Larocque
Laurent Charlin
Travel time is essential for making travel decisions in real-world transportation networks. Understanding its distribution can resolve many … (see more)fundamental problems in transportation. Empirically, single-edge travel-time is well studied, but how to aggregate such information over many edges to arrive at the distribution of travel time over a route is still daunting. A range of statistical tools have been developed for network analysis; tools to study statistical behaviors of processes on dynamical networks are still lacking. This paper develops a novel statistical perspective to specific type of mixing ergodic processes (travel time), that mimic the behavior of travel time on real-world networks. Under general conditions on the single-edge speed (resistance) distribution, we show that travel time, normalized by distance, follows a Gaussian distribution with universal mean and variance parameters. We propose efficient inference methods for such parameters, and consequently asymptotic universal confidence and prediction intervals of travel time. We further develop path(route)-specific parameters that enable tighter Gaussian-based prediction intervals. We illustrate our methods with a real-world case study using mobile GPS data, where we show that the route-specific and universal intervals both achieve the 95\% theoretical coverage levels. Moreover, the route-specific prediction intervals result in tighter bounds that outperform competing models.
2020-04-22
(published)
www.semanticscholar.org