5 papers
Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units
Robin San Roman, Manel Khentout, Tu Anh Nguyen +3
Representation learning has attracted great atten- tion and managed to reach good performances as a pretraining method for downstream tasks or as a first step towards unsu- pervise…
EgoBabyVLM: Benchmarking Cross-Modal Learning from Naturalistic Egocentric Video Data
Dongyan Lin, Phillip Rust, Angel Villar Corrales +19
Children acquire language grounding with remarkable robustness from limited visuo-linguistic input in ways that surpass today's best large multimodal models. Recent research sugges…
DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units
Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo +3
We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to sp…
MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery
Angelo Ortiz Tandazo, Manel Khentout, Youssef Benchekroun +2
This paper introduces MauBERT, a multilingual extension of HuBERT that leverages articulatory features for robust cross-lingual phonetic representation learning. We continue HuBERT…
Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity
Loann Peurey, Marvin Lavechin, Tarek Kunze +4
Audio-recordings collected with a child-worn device are a fundamental tool in child language research. Long-form recordings collected over whole days promise to capture children's…