2025/09/06 by Marvin Lavechin, Lavechin, Marvin, Thomas Hueber +1 · 1 voice
Engineering · Psychology · #Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #Phonetics and Phonology Research #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2509.05849
openalex publication_date 2025/09/06 · arxiv published 2025/09/06 · arxiv updated 2025/09/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 pre-trained 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.