Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors
Advances in Child Development and Behavior · 2026 · 157-198
DOI: 10.1016/bs.acdb.2026.03.001 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Advances in Child Development and Behavior, 2026. Verfasst von Okko Räsänen. Beteiligte Einrichtung: Signal Processing Research Centre, Tampere University, Tampere, Finland. Electronic address: okko.rasanen@tuni.fi. Hauptthemen laut MEDLINE: Language Development, Speech Perception, Computer Simulation, Visual Perception. Die Arbeit nennt 120 Literaturangaben.
Abstract (Originalsprache)
Learning to understand speech appears almost effortless for typically developing infants, yet from an information-processing perspective, acquiring a language from acoustic speech is an enormous challenge. This chapter reviews recent developments in using computational models to understand early language acquisition from speech and audiovisual input. The focus is on self-supervised and visually grounded models of perceptual learning. We show how these models are becoming increasingly powerful in learning various aspects of speech without strong linguistic priors, and how many features of early language development can be explained through a shared set of learning principles-principles broadly compatible with multiple theories of language acquisition and human cognition. We also discuss how modern learning simulations are gradually becoming more realistic, both in terms of input data and in linking model behavior to empirical findings on infant language development.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Signal Processing Research Centre, Tampere University, Tampere, Finland. Electronic address: okko.rasanen@tuni.fi.
Zitieren
APA
Räsänen, O. (2026). Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors. Advances in Child Development and Behavior, 157-198. https://doi.org/10.1016/bs.acdb.2026.03.001
Vancouver
Räsänen O. Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors. Advances in Child Development and Behavior. 2026:157-198. doi:10.1016/bs.acdb.2026.03.001
BibTeX
@article{Rsnen2026,
author = {Räsänen, Okko},
title = {Computational modeling of early language learning from acoustic speech and audiovisual input without linguistic priors},
journal = {Advances in Child Development and Behavior},
year = {2026},
pages = {157--198},
doi = {10.1016/bs.acdb.2026.03.001}
}
EUVIMED