Automated Sex Classification of Children's Voices and Changes in Differentiating Factors with Age

TL;DR

This study developed a machine learning model using acoustic features to classify the sex of children aged 5-15 with high accuracy, revealing age-related and speech-type differences in classification factors.

Contribution

It introduces an optimal feature set and demonstrates that age-specific models and spontaneous speech improve sex classification accuracy in children.

Findings

Higher accuracy for older children and age-specific models.

Spontaneous speech yields better classification cues than scripted speech for younger children.

F0 and vocal tract length are key predictors in older age groups.

Abstract

Sex classification of children's voices allows for an investigation of the development of secondary sex characteristics which has been a key interest in the field of speech analysis. This research investigated a broad range of acoustic features from scripted and spontaneous speech and applied a hierarchical clustering-based machine learning model to distinguish the sex of children aged between 5 and 15 years. We proposed an optimal feature set and our modelling achieved an average F1 score (the harmonic mean of the precision and recall) of 0.84 across all ages. Our results suggest that the sex classification is generally more accurate when a model is developed for each year group rather than for children in 4-year age bands, with classification accuracy being better for older age groups. We found that spontaneous speech could provide more helpful cues in sex classification than scripted speech, especially for children younger than 7 years. For younger age groups, a broad range of acoustic factors contributed evenly to sex classification, while for older age groups, F0-related acoustic factors were found to be the most critical predictors generally. Other important acoustic factors for older age groups include vocal tract length estimators, spectral flux, loudness and unvoiced features.