Communication Dans Un Congrès Année : 2025

From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model

Résumé

Human infants face a formidable challenge in speech acquisition: mapping extremely variable acoustic inputs into appropriate articulatory movements without explicit instruction. We present a computational model that addresses the acoustic-to-articulatory mapping problem through self-supervised learning. Our model comprises a feature extractor that transforms speech into latent representations, an inverse model that maps these representations to articulatory parameters, and a synthesizer that generates speech outputs. Experiments conducted in both single-and multi-speaker settings reveal that intermediate layers of a pretrained wav2vec 2.0 model provide optimal representations for articulatory learning, significantly outperforming MFCC features. These representations enable our model to learn articulatory trajectories that correlate with human patterns, discriminate between places of articulation, and produce intelligible speech. Critical to successful articulatory learning are representations that balance phonetic discriminability with speaker invariance -precisely the characteristics of self-supervised representation learning models. Our findings provide computational evidence consistent with developmental theories proposing that perceptual learning of phonetic categories guides articulatory development, offering insights into how infants might acquire speech production capabilities despite the complex mapping problem they face.

Fichier principal
Vignette du fichier
2509.05849v2.pdf (1.91 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05483766 , version 1 (29-01-2026)

Licence

Identifiants

Citer

Marvin Lavechin, Thomas Hueber. From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation model. EMNLP 2025 - Conference on Empirical Methods in Natural Language Processing, Nov 2025, Suzhou, China. pp.23863-23874, ⟨10.18653/v1/2025.emnlp-main.1217⟩. ⟨hal-05483766⟩
243 Consultations
71 Téléchargements

Altmetric

Partager

  • More