DIgital investigation of Phonetic VARiation: large-scale multilingual modeling of lenition and fortition – DIPVAR

The digital revolution, now at the heart of the humanities, has opened up new avenues for the linguistic research. Thanks to digital methods, large collections of data covering natural communication situations and many languages are finally available for study. Our proposal is in line with this direction: we propose to use speech technologies and artificial intelligence methods for the multilingual study of phonetic variation. Specifically, we will study consonant lenition and fortition, which are both sound changes and patterns of synchronic variation. Our hypothesis is that variation is multifactorial and goes beyond classical linguistic measures and that by focusing on variation at the present time we can understand diachronic mechanisms and make assumptions about future changes. We propose to merge linguistic approaches and numerical methods, including techniques based on speech recognition and machine learning, in a project dedicated to language exploration that combines acoustic and prosodic descriptions and typological perspective. DIPVAR is of interest to linguistics, digital humanities and speech technologies.