CHARACTERIZING NON-NATIVE FRENCH ACCENTS USING AUTOMATIC ALIGNMENT

Bianca Vieru-Dimulescu, Philippe Boula de Mareüil & Martine Adda-Decker
LIMSI-CNRS

ID 1242
[full paper]

The goal of this study is to investigate the most relevant cues that differentiate foreign accents in French (Arabic, English, German, Italian, Spanish and Portuguese). We took advantage of automatic alignment into phonemes of non-native French recordings. Starting from standard acoustic models, we introduced pronunciation variants which were reminiscent of foreign-accented speech: first allowing alternations between French phonemes (e.g. [s]~[z]), then combining them with foreign acoustic units (e.g. a rolled r). Results reveal discriminating accent-specific pronunciations which, to a large extent, confirm both linguistic predictions and human listeners’ judgments.