From May 1, 2022 to July 31, 2022
UNIZAR and CENATAV will joint efforts to create and extend corpora and tools for under-resourced tasks. In this case, the researchers will participate in the creation of the THALENTO database, a corpus that will allow researchers all over the World the analysis and development of procedures and tools to identify and mitigate the effects of speech and language disorders on the use of nowadays speech technologies.
Additionally, they will develop tools, algorithms and baseline systems for speech pathology classification for the corpus THALENTO and for other well-known corpora such as the Saarbruecken Voice Database, The VOICED (VOice ICar fEDerico II) Database or The Advanced Voice Function Assessment Databases (AVFAD).
