3 papers
cs.CL2026
Using the Mimi codec for metalinguistic representations
Artem Saloev, Erin Pacquetet, Nicolas Ballier
In this paper, we focus on the dictionary of 2048 tokens used in Mimi semantic token codebook, the neural codec of the Moshi language model. We show that the ABX experiment carried…
cs.CL2026
Modeling turn-taking with distant viewing: investigating silence thresholds in human and AI-generated discourse
Taylor Arnold, Nicolas Ballier, Artem Saloev
This study investigates silence gaps in two kinds of audiovisual material. We analysed thirty US situational comedies and fifty-one synthetic podcasts generated with Google Noteboo…
cs.CL2025
Assessing the validity of new paradigmatic complexity measures as criterial features for proficiency in L2 writings in English
Cyriel Mallart, Andrew Simpkin, Nicolas Ballier +5
This article addresses Second Language (L2) writing development through an investigation of new grammatical and structural complexity metrics. We explore the paradigmatic productio…