Infant Vocal Tract Development Analysis and Diagnosis by Cry Signals with CNN Age Classification

Abstract

From crying to babbling and then to speech, infants’ vocal tract goes through anatomic restructuring. In this paper, we propose a non-invasive fast method of using infant cry signals with convolutional neural network (CNN) based age classification to diagnose the abnormality of vocal tract development as early as 4-month age. We study F0, F1, F2, spectrograms of the audio signals and relate them to the postnatal development of infant vocalization. We perform two age classification experiments: vocal tract development experiment and vocal tract development diagnosis experiment. The vocal tract development experiment trained on Baby2020 database discovers the pattern and tendency of the vocal tract changes, and the result matches the anatomical development of the vocal tract. The vocal tract development diagnosis experiment predicts the abnormality of infant vocal tract by classifying the cry signals into younger age category. The diagnosis model is trained on healthy infant cries from Baby2020 database. Cries from other infants in Baby2020 and Baby Chillanto database are used as testing sets. The diagnosis experiment yields 79.20% accuracy on healthy infants, 84.80% asphyxiated infant cries and 91.20% deaf cries are diagnosed as cries younger than 4-month although they are from infants up to 9-month-old. The results indicate the delayed developed cries are associated with abnormal vocal tract development.