Automated analysis of newborn cry: relationships between melodicshapes and native language

tRecent research studies have shown that since the last trimester of pregnancy human fetuses are able tolisten to and possibly memorize auditory stimuli from the external world, both as music and language areconcerned. In particular, they exhibit a specific sensitivity to prosodic features such as melody, intensity,and rhythm that are essential for an infant to learn and develop the native language. This paper presentsfirst results concerning the automated mother language identification of a set of about 7500 cry unitscoming from French, Arabic and Italian mother-tongue healthy full term newborns. Acoustical parametersand 12 different melodic shapes are computed with the BioVoice software tool and their classification isperformed with Random Forest and 4 neuro-fuzzy classifiers. Results show up to 95% differences amongthe three languages