Algorithmes d'apprentissage profond adaptatifs en temps réel pour la réhabilitation de la parole à l'aide d'interfaces cerveau-ordinateur implantables // Real-time adaptive deep-learning algorithms for speech rehabilitation with implantable brain-computer
ABG-131533
ADUM-65477 |
Thesis topic | |
2025-04-29 | Public funding alone (i.e. government, region, European, international organization research grant) |
Université Grenoble Alpes
La Tronche Cedex - Auvergne-Rhône-Alpes - France
Algorithmes d'apprentissage profond adaptatifs en temps réel pour la réhabilitation de la parole à l'aide d'interfaces cerveau-ordinateur implantables // Real-time adaptive deep-learning algorithms for speech rehabilitation with implantable brain-computer
- Biology
Machine learning, Parole, Neurotechnologie, Handicap, Syndrôme d'enfermement
Machine learning, Speech, Neurotechnology, Handical, Locked-In Syndrome
Machine learning, Speech, Neurotechnology, Handical, Locked-In Syndrome
Topic description
Environ 18,5 millions de personnes souffrent d'un trouble de la parole, de la voix ou du langage dans le monde, et environ 300 000 en France. Parmi eux, plusieurs millions souffrent de troubles de la parole dus à des maladies neurodégénératives (telles que la sclérose latérale amyotrophique - SLA) ou à des accidents vasculaires cérébraux qui endommagent les voies motrices dédiées à l'articulation et à l'émission de la voix. Ces déficiences peuvent déboucher sur un syndrome d'enfermement (LIS), dans lequel les personnes sont incapables de parler alors que leurs capacités cognitives restent intactes. Dans ce contexte, les systèmes d'interface cerveau-ordinateur (BCI) visent à fournir des solutions de communication à ces personnes en enregistrant leurs signaux cérébraux et en les « traduisant » en parole artificielle produite par un synthétiseur [1], [2], [3], [4], [5], [6], [7], [8]. Nos recherches actuelles se concentrent sur le développement d'un BCI vocal entièrement implantable qui reconstruit la parole à partir de signaux électrocorticographiques intracrâniens (ECoG) en temps réel en utilisant l'apprentissage profond [9], [10], [11]. L'objectif de la thèse sera de développer des algorithmes adaptatifs basés sur des réseaux neuronaux profonds qui décodent la parole à partir des signaux ECoG en se mettant à jour en temps réel, et d'évaluer ces algorithmes chez des patients chroniquement implantés avec des implants cérébraux sans fil.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Approximately 18.5 million individuals have a speech, voice, or language disorder worldwide, and about 300,000 in France. Among them, several millions have speech disability secondary to neurodegenerative diseases (such as Amyotrophic Lateral Sclerosis – ALS) or brainstem strokes damaging motor pathways dedicated to speech articulation and voicing. These impairments may result in a locked in syndrome (LIS), where people are unable to speak while their cognitive abilities remain intact. In this context, brain-computer interface (BCI) systems aim to provide communication solutions for these people by recording their brain signals and “translating” them into artificial speech produced by a synthesizer [1], [2], [3], [4], [5], [6], [7], [8]. Our current research is focused on the development of a fully implantable speech BCI that reconstructs speech from intracranial electrocorticographic (ECoG) signals in real time using deep learning [9], [10], [11]. The goal of the thesis will be to develop adaptive algorithms based on deep neural networks that decode speech from ECoG signals and update in real time, and evaluate these algorithms with patients chronically implanted with wireless brain implants.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Début de la thèse : 01/10/2025
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Approximately 18.5 million individuals have a speech, voice, or language disorder worldwide, and about 300,000 in France. Among them, several millions have speech disability secondary to neurodegenerative diseases (such as Amyotrophic Lateral Sclerosis – ALS) or brainstem strokes damaging motor pathways dedicated to speech articulation and voicing. These impairments may result in a locked in syndrome (LIS), where people are unable to speak while their cognitive abilities remain intact. In this context, brain-computer interface (BCI) systems aim to provide communication solutions for these people by recording their brain signals and “translating” them into artificial speech produced by a synthesizer [1], [2], [3], [4], [5], [6], [7], [8]. Our current research is focused on the development of a fully implantable speech BCI that reconstructs speech from intracranial electrocorticographic (ECoG) signals in real time using deep learning [9], [10], [11]. The goal of the thesis will be to develop adaptive algorithms based on deep neural networks that decode speech from ECoG signals and update in real time, and evaluate these algorithms with patients chronically implanted with wireless brain implants.
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Début de la thèse : 01/10/2025
Funding category
Public funding alone (i.e. government, region, European, international organization research grant)
Funding further details
Concours pour un contrat doctoral
Presentation of host institution and host laboratory
Université Grenoble Alpes
Institution awarding doctoral degree
Université Grenoble Alpes
Graduate school
216 ISCE - Ingénierie pour la Santé la Cognition et l'Environnement
Candidate's profile
Les candidats doivent être très motivés et posséder une solide formation en informatique, en apprentissage automatique, en intelligence artificielle et en traitement du signal. De solides compétences en programmation en Python sont requises. Une bonne autonomie et une capacité à travailler en équipe interdisciplinaire ainsi qu'une bonne maîtrise de l'anglais écrit et parlé sont requises, tandis qu'aucune connaissance spécifique du français n'est obligatoire.
Candidates should be highly motivated with a solid training in computer science, machine learning, artificial intelligence, and signal processing. Strong programming skills in Python are required. A good autonomy and ability for interdisciplinary team work and fluent proficiency in English writing and speaking are required while no specific knowledge of French is mandatory.
Candidates should be highly motivated with a solid training in computer science, machine learning, artificial intelligence, and signal processing. Strong programming skills in Python are required. A good autonomy and ability for interdisciplinary team work and fluent proficiency in English writing and speaking are required while no specific knowledge of French is mandatory.
2025-05-23
Apply
Close
Vous avez déjà un compte ?
Nouvel utilisateur ?
More information about ABG?
Get ABG’s monthly newsletters including news, job offers, grants & fellowships and a selection of relevant events…
Discover our members
MabDesign
ONERA - The French Aerospace Lab
Généthon
MabDesign
Nokia Bell Labs France
ADEME
CASDEN
Tecknowmetrix
PhDOOC
Ifremer
Aérocentre, Pôle d'excellence régional
Groupe AFNOR - Association française de normalisation
ANRT
TotalEnergies
ASNR - Autorité de sûreté nucléaire et de radioprotection - Siège
CESI
Institut Sup'biotech de Paris
Laboratoire National de Métrologie et d'Essais - LNE
SUEZ
-
Thesis topicRef. 129914AUBIERE , Auvergne-Rhône-Alpes , FranceUniversité Clermont Auvergne
Synthèse enzymatique d'hydroxycétones valorisables // Enzymatic synthesis of valuable hydroxyketones
Scientific expertises :Chemistry - Biochemistry - Biotechnology
-
JobRef. 131050, Ile-de-France , FranceSupBiotech
Directeur des Laboratoires d'Enseignements (H/F)
Scientific expertises :Biotechnology - Biology
Experience level :Confirmed