@inproceedings{moscoso-del-prado-martin-salhan-2026-modelling,
    title = "Modelling the Diachronic Emergence of Phoneme Frequency Distributions",
    author = "Moscoso Del Prado Martin, Fermin  and
      Salhan, Suchir",
    editor = "Voigt, Rob  and
      Warstadt, Alex  and
      Feldman, Naomi  and
      Linzen, Tal",
    booktitle = "Proceedings of the Society for Computation in Linguistics 2026",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.14/",
    pages = "138--146",
    ISBN = "979-8-89176-412-5",
    abstract = {Phoneme frequency distributions exhibit robust statistical regularities across languages, including exponential-tailed rank-frequency patterns and a negative relationship between phonemic inventory size and the relative entropy of the distribution. The origin of these patterns remains largely unexplained. In this paper, we investigate whether they can arise as consequences of the historical processes that shape phonological systems. We introduce a stochastic model of phonological change and simulate the diachronic evolution of phoneme inventories. A na{\"i}ve version of the model reproduces the general shape of phoneme rank-frequency distributions but fails to capture other empirical properties. Extending the model with two additional assumptions {--}an effect related to frequency and a stabilising tendency toward a preferred inventory size{--} yields simulations that match both the observed distributions and the negative relationship between inventory size and relative entropy. These results suggest that some statistical regularities of phonological systems may arise as a result of diachronic sound change instead of {--}or in addition to{--} explicit optimisation or compensatory mechanisms.}
}