Artificial sound change: Language change and deep convolutional neural networks in iterative learning
Gasper Begus
September 2021

This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated raw speech data. The paper argues that several properties of sound change emerge from the proposed architecture. GANs (Goodfellow et al., 2014; Donahue et al., 2019) are uniquely appropriate for modeling language change because the networks are trained on raw unsupervised acoustic data, contain no language-specific features and, as argued in Beguš (2020), encode phonetic and phonological representations in their latent space and generate linguistically informative innovative data. The first generation of networks is trained on the relevant sequences in human speech from TIMIT. The subsequent generations are not trained on TIMIT, but on generated outputs from the previous generation and thus start learning from each other in an iterative learning task. The initial allophonic distribution is progressively being lost with each generation, likely due to pressures from the global distribution of aspiration in the training data. The networks show signs of a gradual shift in phonetic targets characteristic of a gradual phonetic sound change. At endpoints, the outputs superficially resemble a phonological change — rule loss.
Format: [ pdf ]
Reference: lingbuzz/005558
(please use that when you cite this article)
Published in: Submitted. Note change of title: Deep Sound Change: Deep and Iterative Learning, Convolutional Neural Networks, and Language Change
keywords: artificial intelligence, deep convolutional neural networks, generative adversarial networks, speech, phonetic learning, phonological learning, historical linguistics, sound change, phonology
previous versions: v1 [November 2020]
Downloaded:341 times


[ edit this article | back to article list ]