BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

Théo Charlot; Tarek Kunze; Maxime Poli; Alejandrina Cristia; Emmanuel Dupoux; Marvin Lavechin

eess.ASSep 18, 2025

BabyHuBERT: Multilingual Self-Supervised Learning for Segmenting Speakers in Child-Centered Long-Form Recordings

Authors: Théo Charlot, Tarek Kunze, Maxime Poli, Alejandrina Cristia, Emmanuel Dupoux, Marvin Lavechin

Organizations: LSCP, DEC, ENS, EHESS, CNRS, PSL University, France · Laboratoire d’Informatique et Syst`emes, Universit´e Aix-Marseille, CNRS, France

Abstract

Child-centered daylong recordings are essential for studying early language development, but existing speech models trained on clean adult data perform poorly due to acoustic and linguistic differences. We introduce BabyHuBERT, a self-supervised speech model trained on 13,000 hours of multilingual child-centered recordings from 40+ languages. Evaluated on voice type classification, the task of identifying who produces speech and when in child-centered recordings (key child, other children, male, and female adults), BabyHuBERT-VTC achieves F1-scores from 55.0% to 76.1% across six corpora, consistently outperforming W2V2-LL4300 and HuBERT (pretrained on English daylongs and clean adult speech, respectively). Notable gains include 14.0 and 18.3 absolute F1 points over HuBERT on Vanuatu and Solomon Islands, demonstrating effectiveness on underrepresented languages. We share code and models to support researchers working with child-centered recordings across diverse linguistic contexts.

Explore similar work

Context-aware child-directed speech detection from long-form recordings
May 31, 2026Théo Charlot, Tarek Kunze, Kaveri K. Sheth +2Speaker Recognition
How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures
Jun 20, 2026Abhijit Sinha, Hemant Kumar Kathania, Mohit Joshi +3Self-Supervised Speech Models Wav2Vec
MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery
Dec 22, 2025Angelo Ortiz Tandazo, Manel Khentout, Youssef Benchekroun +2Self-Supervised Speech Models Articulatory

May 31, 2026 · eess.ASJ/K move · Enter open · S save

Context-aware child-directed speech detection from long-form recordings

Théo Charlot, Tarek Kunze, Kaveri K. Sheth, Alejandrina Cristia+1

Automatically distinguishing child-directed speech from adult-directed speech in long-form recordings is key to scalable analyses of children's language environments. Existing approaches process utterances in isolation and have been evaluated primarily on English. We address these gaps along three dimensions. First, we fine-tune and evaluate six-self supervised models on a multilingual dataset of 182 children, showing that in-domain pre-training on child-centered recordings substantially outperforms models trained on adult speech. Second, we demonstrate that incorporating surrounding context substantially improves classification, with an absolute gain of 13.8% in average F1-score. Third, we evaluate our model in a realistic end-to-end pipeline, from adult speech detection to addressee classification, showing that performance drops under automatic segmentation but still consistently outperforms a rule-based baseline.

Speaker Recognition

Open paper Ask about it PDF

Abstract

Explore similar work

Context-aware child-directed speech detection from long-form recordings

How Well Do Self-Supervised Speech Models Encode Age and Gender in Children's Speech? A Layer-Wise Analysis Across Multiple Architectures

MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery