Afra Alishahi — accepted AI-conference papers

2024

Encoding of lexical tone in self-supervised models of spoken language

Gaofei Shen, Michaela Watkins, Afra Alishahi, Arianna Bisazza, Grzegorz Chrupała

NAACL 2024long

Interpretability research has shown that self-supervised Spoken LanguageModels (SLMs) encode a wide variety of features in human speech from theacoustic, phonetic, phonological, syntactic and semantic levels, to speakercharacteristics. The bulk of prior research on representations of phonologyhas fo…

Cited by 5 Source ↗PDF ↗Scholar ↗

2023

Homophone Disambiguation Reveals Patterns of Context Mixing in Speech Transformers

Hosein Mohebbi, Grzegorz Chrupała, Willem Zuidema, Afra Alishahi

EMNLP 2023long main

Transformers have become a key architecture in speech processing, but our understanding of how they build up representations of acoustic and linguistic structure is limited. In this study, we address this gap by investigating how measures of 'context-mixing' developed for text models can be adapted…

Cited by 0 Source ↗code ↗Scholar ↗