The next seminar of the Cornet team will take place on February 23, 2024, at 11:35 a.m. in S3, and will consist of two parts. First, Sylvie Chaddad (LIA) will present her thesis topic on Stochastic Control for Optimizing Crowdfunding Project Dynamics. Then, Lorena Garrido (University of Veracruz) will present her work titled On the Monge-Kantorovich divergence. Abstract: The Monge-Kantorovich divergence is a measure of closeness between probability distributions. Historically, it arises from an optimal transport problem of sand movement, in the area of civil engineering. Today, the Monge-Kantorovich problem has given rise to many theoretical studies, as well as various applications, including data analysis. In this talk, a couple of applications in data analysis will be mentioned.
Thibault Roux will organize a debate on the subject mentioned below: “Recent advances in technology have raised many questions and concerns about their impact on our societies. Many people are concerned about military use, mass surveillance or disinformation. From a more global perspective, Nick Bostrom, a philosopher, theorizes the vulnerable world hypothesis which predicts that science will destroy humanity.In this debate, we will question our own biases as researchers and try to answer the ethical questions raised by this hypothesis. Is science a threat to humanity? Should we stop science? Or more seriously, can we find a solution to prevent ourselves from self-destruction ?”
The next seminar of the Cornet team will take place on January 31, 2024, at 11:35 am in S3 and will consist of two parts. Firstly, Felipe Albuquerque (LIA) will present his thesis topic on ‘The p-Median Problem with Coverage Constraints: New Resolution Methods and Application to the Design of Public Services.’ Following that, Luca Dini and Pierre Jourlin will present their ongoing work on the theme of ‘Hybrid Methods for Cognitive Attitudes Detection.’ Summary: In this seminar, we will present ongoing work on the transformation of a keyword spotting system into a concept-based labeling engine. We will highlight four major axes of this work:
The next SLG meeting will take place in room S5 on Thursday, February 1st, from 12:00 PM to 1:00 PM. Ryan Whetten will present his work, and you can find a brief introduction below. ——————————————————————— Open Implementation and Study of BEST-RQ for Speech Processing Abstract: Self-Supervised Learning (SSL) has proven to be useful in various speech tasks. However, these methods are generally very demanding in terms of data, memory, and computational resources. Recently, Google came out with a model called BEST-RQ (BERT-based Speech pre-Training with Random-projection Quantizer). Despite BEST-RQ’s great performance and simplicity, details are lacking in the original paper and there is no official easy-to-use open-source implementation. Furthermore, BEST-RQ has not been evaluated on other downstream tasks aside from ASR. In this presentation, we will discuss the details of my implementation of BEST-RQ and then see results from our preliminary study on four downstream tasks. Results show that a random projection quantizer can achieve similar downstream performance as wav2vec 2.0 while decreasing training time by over a factor of two.
On Friday, January 19th, at 11:35 in room S6, we will have three short presentations:
On 18 January from 12 am, we will host a talk from Dr. Paul Gauthier Noé on « Explaining probabilistic predictions … ». The presentation will be hosted on room S6. More details will follow Bio: Paul Gauthier Noe just received a PhD in Computer Science in Avignon Université under the supervision of Prof. Jean-François Bonastre and Dr. Driss Matrouf. He was working for the international JST-ANR VoicePersonae project and his main research interests are Speaker verification, Bayesian decision theory, Calibration of probabilities and Privacy in Speech.
On 12 January from 12 am, we will host a virtual talk from Dr. Fenna Poletiek from Institute of Psychology at Leiden University on « Language learning in the lab ». The presentation will be hosted on room S6. Abstract: Language learning in the lab Language learning skills have been considered a defining feature of humanness. In this view language cannot be acquired by mere associative or statistical learning processes, only, like many other skills are learned by human and nonhuman primates during development. Indeed, the high (recursive) complexity of human grammars have been shown to make them impossible to learn by exposure to language exemplars only. Some research suggests, however, that at least some statistical learning is recruited in language acquisition (Perruchet & Pacton, 2006). And primates have been shown to mimic complex grammatical patterns after being trained on a sequence of stimulus responses (Rey et al., 2012). We performed series of studies with artificial languages in the lab, to investigate associative and statistical learning processes that support language learning. The results thus far suggest a fine tuned cooperation between three crucial features of the natural language learning process: first, learning proceeds ‘starting small’ with short simple sentences growing in complexity Plus d'infos
The next SLG meeting will be held in room S1 on Thursday, December 21st, from 12:00 PM to 1:00 PM. We will have the pleasure of hosting St Germes BENGONO OBIANG, a PhD student in speech processing, focusing on tone recognition in under-resourced languages. He is supervised by Norbert TSOPZE and Paulin MELATAGIA from the University of Yaoundé 1, as well as by Jean-François BONASTRE and Tania JIMENEZ from LIA. Abstract: Many sub-Saharan African languages are categorized as tone languages and for the most part, they are classified as low resource languages due to the limited resources and tools available to process these languages. Identifying the tone associated with a syllable is therefore a key challenge for speech recognition in these languages. We propose models that automate the recognition of tones in continuous speech that can easily be incorporated into a speech recognition pipeline for these languages. We have investigated different neural architectures as well as several features extraction algorithms in speech (Filter banks, Leaf, Cestrogram, MFCC). In the context of low-resource languages, we also evaluated Wav2vec models for this task. In this work, we use a public speech recognition dataset on Yoruba. As for the results, using the Plus d'infos
In the context of team Cornet’s seminars, Andrea Fox (LIA) will present his research work on Safe Reinforcement Learning for Video Admission Control, on December 8, 2023, at 11:35 in the meeting room. Abstract: Mobile video cameras have become a pervasive commodity and represent an important candidate source to enhance video analytic applications. Yet, while available in large quantities, the limitations of the edge computing infrastructure require the careful selection of which video flows to process at any point in time to maximize the amount of information extracted by deployed applications. In this paper, we present an admission control scheme for mobile video streams originating from different areas and dispatched to multiple processing servers over an edge computing infrastructure. We introduce a model rooted in the theory of Constrained Markov Decision Processes (CMDPs) that captures the problem of ensuring adequate area coverage to applications, while accounting for constraints of edge servers and access network capacity. On top of this model, we develop two new policies based on specialized primal-dual constrained Reinforcement Learning methods that solve the optimal admission control problem. The first, called DR-CPO, adopts reward decomposition reinforcement learning. This technique effectively mitigates state-space explosion, achieves optimality, and significantly accelerates Plus d'infos
In the context of team Cornet’s seminars, Olivier Bilenne (LIA) will present his research work on Implementing fictitious play in partially observable stochastic games, on November 24, 2023, 11:35 in the meeting room. Abstract: Extensions of fictitious play to stochastic games have been recently examined in combination with reinforcement learning techniques inherent to Markov decision processes. We revisit this approach in the context of partially observable stochastic games. For this, we consider a two-player (finite-state) zero-sum stochastic game where one player (the attacker) has full visibility of the system, whereas the other player (the defender) has no access to the state of the opponent and must instead compose with public sources of information (in our setting: the actions played and their associated payoffs). We study a fictitious play dynamics where the players best response to the estimated empirical frequencies of action of their opponent. This sequence of play requires from the players to form beliefs on both their opponent’s strategy and on their own continuation payoff (modeled by a Q-function), based on the (full or partial) information that is available to them. The strategy estimation scheme, in particular, features a correction mechanism making up for delayed symptoms in the partially Plus d'infos