A5080082961- Dysphagia Assessment and Management
- Voice and Speech Disorders
- Obstructive Sleep Apnea Research
- Speech Recognition and Synthesis
- Health, Medicine and Society
- Natural Language Processing Techniques
- Neurobiology of Language and Bilingualism
- Phonetics and Phonology Research
- Topic Modeling
- Neuroscience of respiration and sleep
- Phonocardiography and Auscultation Techniques
- French Language Learning Methods
- Respiratory Support and Mechanisms
- Text Readability and Simplification
Institut Polytechnique de Bordeaux
2021-2024
Université Toulouse - Jean Jaurès
2021-2024
Université Toulouse III - Paul Sabatier
2021-2024
Institut de Recherche en Informatique de Toulouse
2021-2024
Université Toulouse-I-Capitole
2021-2024
Centre National de la Recherche Scientifique
2024
Automatic detection and identification of pharynxgolaryngeal activities (PLA) such as swallowing, speaking, coughing, are crucial steps in developing a system for diagnosing dysphagia (swallowing disorders) using high-resolution cervical auscultation (HRCA) signals. Using sensors placed on the throat, HRCA provides clinicians with non-invasive means assessing swallowing. This study introduces new approach based depthwise CNN LSTM networks to automatically detect identify PLA synchronized...
Discourse segmentation, the first step of discourse analysis, has been shown to improve results for text summarization, translation and other NLP tasks. While segmentation models written tend perform well, they are not directly applicable spontaneous, oral conversation, which linguistic features foreign text. Segmentation is less studied this type language, where annotated data scarce, existing corpora more heterogeneous. We develop a weak supervision approach adapt, using minimal...