The SMILE Continuous DSGS Corpus: A Resource for Longitudinal Exploration of Continuous Swiss German Sign Language

Abstract

This paper presents the SMILE Continuous DSGS Corpus, a longitudinal dataset that allows for investigating how hearing adults acquire Swiss German Sign Language as a second language. It includes recordings of sign language learners and native signer controls collected at four points over a period of 18 months and annotated for manual and non-manual components, errors, and sentence-level acceptability. The resource provides high-quality, synchronized video suitable for both linguistic and automatic sign language processing research, for example, supporting studies of interlanguage development and training of automatic sign language recognition models. We present here an exploratory analysis of the learner subcorpus using Bayesian mixed-effects modeling. The corpus and accompanying annotations are available for research purposes under a Creative Commons license (CC BY-NC-SA 4.0).

Resources

Details