This paper presents first results concerning the mother language assessment of a set of about 7.500 cry units coming from French, Arabic and Italian mother-tongue healthy at term newborns. A number of acoustical parameters and 12 different melodic shapes are detected with the BioVoice SW tool and their classification is performed with Random Forest and 4 neuro-fuzzy classifiers. Results show up to 94% differences among the three languages.
RELATIONSHIPS BETWEEN NEWBORNS' CRY MELODY SHAPES AND NATIVE LANGUAGE / C.Manfredi, G.Pieraccini, R.Viellevoye, A.Torres-García, C.A. Reyes-García. - STAMPA. - (2017), pp. 47-50. (Intervento presentato al convegno 10th Int. Workshop Models and Analysis of Vocal Emissions for Biomedical Applications, tenutosi a Firenze, Italy nel 13-15 Dec., 2017) [10.36253/978-88-6453-607-1].
RELATIONSHIPS BETWEEN NEWBORNS' CRY MELODY SHAPES AND NATIVE LANGUAGE
C. Manfredi;
2017
Abstract
This paper presents first results concerning the mother language assessment of a set of about 7.500 cry units coming from French, Arabic and Italian mother-tongue healthy at term newborns. A number of acoustical parameters and 12 different melodic shapes are detected with the BioVoice SW tool and their classification is performed with Random Forest and 4 neuro-fuzzy classifiers. Results show up to 94% differences among the three languages.File | Dimensione | Formato | |
---|---|---|---|
MAVEBA2017_Viellevoye_2_2628_6170.pdf
accesso aperto
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Open Access
Dimensione
363.33 kB
Formato
Adobe PDF
|
363.33 kB | Adobe PDF |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.