@inproceedings{saloev-etal-2026-using,
    title = "Using the Mimi codec for metalinguistic representations",
    author = "Saloev, Artem  and
      Pacquetet, Erin  and
      Ballier, Nicolas",
    editor = "Bernard, Timoth{\'e}e  and
      Chersoni, Emmanuele  and
      Rambelli, Giulia",
    booktitle = "Proceedings of the Third Workshop on the Bridges and Gaps between Formal and Computational Linguistics ({B}ri{G}ap-3)",
    month = jul,
    year = "2026",
    address = "Paris, France",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-brigap/2026.brigap-1.7/",
    pages = "63--73",
    ISBN = "XXX-X-XXXXXX-XX-X",
    abstract = "Codec-based audio language models are developing, but little explainability research has been dedicated to the representation of this type of speech tokenisation. In this paper, we focus on the dictionary of 2048 tokens used in Mimi{'}s semantic token codebook, the neural codec of the Moshi language model (D{\'e}fossez et al., 2024). We show that the ABX experiment carried out with Mimi fails to capture the mapping of the semantic tokens to phone realisations. By realigning Mimi{'}s representations to the TIMIT corpus transcriptions (Garofolo et al., 1993), we show that the 2048 tokens IDs of the semantic codebook map to quadphone, triphone, biphone, phone and subphone realisations. We used the TIMIT transcriptions as evidence of the validity of the allophone-based representations of these 80ms semantic token representation and examine some of the theoretical consequences for the tokenisation of speech at allophone and subphonemic level."
}