Perception Point: Identifying Critical Learning Periods in Speech for Bilingual Networks
Anuj Saraswat, Mehar Bhatia, Yaman Kumar Singla, Changyou Chen, Rajiv, Ratn Shah

TL;DR
This paper investigates how deep neural visual lip-reading models develop speech perception abilities, revealing parallels with cognitive psychology's critical periods in bilingual and monolingual infants through experiments on large datasets.
Contribution
It introduces a novel analysis linking neural network development in speech perception to cognitive psychology theories of critical periods in language acquisition.
Findings
Strong correlation between cognitive theories and neural model development
Models exhibit phases similar to human speech perception development
Insights into critical periods for bilingual and monolingual speech perception
Abstract
Recent studies in speech perception have been closely linked to fields of cognitive psychology, phonology, and phonetics in linguistics. During perceptual attunement, a critical and sensitive developmental trajectory has been examined in bilingual and monolingual infants where they can best discriminate common phonemes. In this paper, we compare and identify these cognitive aspects on deep neural-based visual lip-reading models. We conduct experiments on the two most extensive public visual speech recognition datasets for English and Mandarin. Through our experimental results, we observe a strong correlation between these theories in cognitive psychology and our unique modeling. We inspect how these computational models develop similar phases in speech perception and acquisitions.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsLanguage Development and Disorders · Phonetics and Phonology Research · Multilingual Education and Policy
