Laetitia Jeancolas is currently a postdoctoral fellow at Concordia University. Her main project, done in collaboration with Paris Brain Institute (ICM) and IM2A, focuses on multimodal predictive modeling of Alzheimer’s disease (INSIGHT cohort). Specifically, Laetitia studies the neurovascular coupling in participants with subjective memory loss. She is also specialized in the analysis of voice impairments in neurodegenerative diseases and their use for automatic and early detection and disease monitoring. Her research interests are wide-ranging, centering around the use of signal processing, machine learning and neuroimaging techniques for the early detection of neurodegenerative diseases and the understanding of their mechanisms.
Laetitia Jeancolas is a former student of Ecole Normale Supérieure where she attended a selective program in fundamental physics and received a Master of Science degree in cognitive science. In 2019, she obtained her PhD in signal processing at Télécom SudParis (Paris-Saclay University), in collaboration with ICM. She received the Best PhD award of the Futur & Ruptures Program by the Fondation Mines Télécom, along with several other awards during her PhD.
During her studies, Laetitia Jeancolas worked on several research projects, such as the development of a cognition model in the University of Arizona (USA), or the study of tool use acquisition in infants, at Integrative Neuroscience and Cognition Center (former Laboratoire Psychologie de la Perception, Paris V). She did her M.S research project on brain effective connectivity in early stages of Alzheimer's disease during memory tasks, at ICM and Grenoble Institut des Neurosciences (GIN).
During her PhD, Laetitia Jeancolas worked on the early detection of Parkinson's disease (PD) using voice analysis. She designed the experimental protocol, set up the acquisition tools, collected the data and conducted the analyses. One of the main innovative analyses consisted in adapting a recent deep learning feature extraction technique used in speaker recognition to PD detection. Laetitia also implemented face recordings, to analyze PD hypomimia in the same cohort, as well as a task based functional MRI protocol that enables the investigation of the neural disruptions causing the early PD speech impairments.
She expanded her PhD work during a postdoc at ICM where she focused more precisely on the neural correlates of the Parkinson-related voice impairments. Since, she has continued to work in this field through several collaborations with ICM, Télécom SudParis, Lille university, McGill university and Concordia university, supervising several PhD students, and M.S. research projects, on Parkinson and Alzheimer’s speech impairments and PD hypomimia.
Jeancolas, L., et al., (2022) « Voice Characteristics from Isolated Rapid Eye Movement Sleep Behavior Disorder to Early Parkinson’s Disease ». Parkinsonism & Related Disorders 95 : 86‑91. https://doi.org/10.1016/j.parkreldis.2022.01.003.
Jeancolas L., et al., (2021) « X-Vectors: New Quantitative Biomarkers for Early Parkinson’s Disease Detection From Speech ». Frontiers in Neuroinformatics 15. https://doi.org/10.3389/fninf.2021.578369.
Jeancolas L., et al., (2019) « Comparison of Telephone Recordings and Professional Microphone Recordings for Early Detection of Parkinson’s Disease, Using Mel-Frequency Cepstral Coefficients with Gaussian Mixture Models ». In Interspeech 2019, 3033‑37. Graz, Austria: ISCA. https://doi.org/10.21437/Interspeech.2019-2825.
Jeancolas L., et al., (2022) « Can Infants Generalize Tool Use From Spoon to Rake at 18 Months? » Journal of Motor Learning and Development, 2022, 1‑17. https://doi.org/10.1123/jmld.2022-0006.
Parkinson's disease detection using voice analysis: https://www.youtube.com/watch?v=uJuBqR0duhw
5-min PhD summary: https://www.youtube.com/watch?v=mtt8W1wU8Ig
Fondation Recherche Alzheimer's video on my postdoc project: https://www.youtube.com/watch?v=LXPOjGPjCoQ
