Welcome, Bienvenue !
Update : I will soon start exploring opportunities for what comes next after finishing my PhD. Get in touch!
I am a last year PhD student in Machine Learning and Cognitive Science at the Ecole Normale Supérieure & Université de Paris, under the supervision of Emmanuel Dupoux and Guillaume Wisniewski. I am also currently pursuing an internship at Meta as an AI Research Scientist Intern, in the Paris office.
I am part of the Cognitive Machine Learning team (CoML) at the Laboratoire de Sciences Cognitives et Psycholinguistique (LSCP), in the Cognitive Science Department (DEC) of the Ecole Normale Supérieure (Ulm). I am also affiliated to the Laboratoire de Linguistique Formelle (LLF) at the Université Paris Cité.
Previously, I graduated from the University of Edinburgh with an MSc in Speech and Language Processing, and from City, University of London with a BSc in Psychology. I also worked as a speech recognition engineer, focusing on acoustic modelling, prior to starting my PhD (see my full CV here).
Research Interests
My current research focuses on bilingual language acquisition, from a reverse-engineering perspective. Briefly, it consists in constructing unsupervised models of cognitive behaviours, using the same input available to humans, as a way to draw hypotheses on the actual cognitive processes at stake. More information on this approach is described on the CoML team’s website.
I am a strong advocate for the importance of tying links between the Machine Learning and Psychology communities, as I believe both benefits from getting insights from the other.
I am also currently a part of the committee for the 2021 Zero Resource Speech challenge, which focuses on evaluating unsupervised speech representation models. Check it out!
Latest news
26/06/2023 - [ 💼 INTERNSHIP] I just started a 5 months internship at Meta in the Paris AI research group.
29/05/2023 - [📄 PAPER] Our new paper "Realistic and broad-scope learning simulations: first results and challenges" has just been published in Journal of Child Language! We discuss the future of learning simulations for early language acquisition.
24/02/2023 - [🔎 BENCHMARK] + [📄 PAPER] We just released ProsAudit, a benchmark for evaluating English prosody in SSL models of speech! It is now part of the Zero-Resource speech challenge, and the related preprint is available on ArXiv.
13/12/2022 - [📄 PAPER] Our preprint Statistical learning bootstraps early language acquisition, co-authored with Marvin Lavechin, is available on PsyArxiv.
14/11/2022 - [🤖 SEMINAR] I participated in the GDR LIFT-TAL seminar in Marseille, France.
08/11/2022 - [🗣️ TALK] I presented work on the learning simulations of language acquisition project in the Benchmarking Speech Acquisition in Humans and Machines seminar. Video is available on Youtube.
21/10/2022 - [🤖 SEMINAR] I took part in the one-week Dagstuhl Seminar entitled Developmental Machine Learning: From Human Learning to Machines and Back (also here).
11/10/2022 - [📄 PAPER] Our preprint with Dr. Ansgar Endress The specificity of sequential Statistical Learning is available on PsyArxiv.
18/09/2022 - [📄 PAPER] I was at Interspeech in Incheon, Korea presenting our latest paper Probing phoneme, language and speaker information in unsupervised speech representations.
Get in touch
maureen.deseyssel (at) gmail.com
