The “Speech and Language Group” team brings together researchers and teacher-researchers from the LIA whose object of study is language and, in particular, speech, at the origin of the creation of the LIA. Research activities thus cover the extraction, processing and generation of information conveyed by the speech signal (linguistic and paralinguistic content), speaker recognition and characterization, vocal interactions and multimodality. These activities find their applications in the fields of security and defense, health, media, intelligent and/or embedded objects. Machine learning, including deep learning, as well as data/corpus oriented approaches, are at the heart of research activities.
Projects