Phone Duration Modeling for Speaker Age Estimation in Children

TL;DR

This paper introduces a novel approach for estimating children's speaker age using phone duration features derived from forced alignment, demonstrating robustness across datasets and developmental stages.

Contribution

It proposes a new feature set based on phone durations for children's age estimation, addressing challenges of variability and data scarcity in child speech.

Findings

Phone duration features effectively predict children's age.

The approach is robust across different datasets and age groups.

Certain phonemes are more indicative of age than others.

Abstract

Automatic inference of important paralinguistic information such as age from speech is an important area of research with numerous spoken language technology based applications. Speaker age estimation has applications in enabling personalization and age-appropriate curation of information and content. However, research in speaker age estimation in children is especially challenging due to paucity of relevant speech data representing the developmental spectrum, and the high signal variability especially intra age variability that complicates modeling. Most approaches in children speaker age estimation adopt methods directly from research on adult speech processing. In this paper, we propose features specific to children and focus on speaker's phone duration as an important biomarker of children's age. We propose phone duration modeling for predicting age from child's speech. To enable that, children speech is first forced aligned with the corresponding transcription to derive phone duration distributions. Statistical functionals are computed from phone duration distributions for each phoneme which are in turn used to train regression models to predict speaker age. Two children speech datasets are employed to demonstrate the robustness of phone duration features. We perform age regression experiments on age categories ranging from children studying in kindergarten to grade 10. Experimental results suggest phone durations contain important development-related information of children. Phonemes contributing most to estimation of children speaker age are analyzed and presented.