Do self-supervised speech models develop human-like perception biases?
Juliette Millet, Ewan Dunbar · Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2022
Self-supervised models for speech processing form representational spaces without using any external labels.Increasingly, they appear to be a feasible way of at least partially eliminating costly manual annotations, a problem of particular concern for low-resource languages.But what kind of representational spaces do these models construct?Human perception specializes to the sounds of listeners' native languages.Does the same thing happen in self-supervised models?We examine the representational spaces of three kinds of stateof-the-art self-supervised models: wav2vec 2.0, HuBERT and contrastive predictive coding (CPC), and compare them with the perceptual spaces of French-speaking and Englishspeaking human listeners, both globally and taking account of the behavioural differences between the two language groups.We show that the CPC model shows a small native language effect, but that wav2vec 2.0 and Hu-BERT seem to develop a universal speech perception space which is not language specific.A comparison against the predictions of supervised phone recognisers suggests that all three self-supervised models capture relatively finegrained perceptual phenomena, while supervised models are better at capturing coarser, phone-level, effects of listeners' native language, on perception.