{"pk":28813,"title":"Comparing unsupervised speech learning directly to human performance inspeech perception","subtitle":null,"abstract":"We compare the performance of humans (English and Frenchlisteners) versus an unsupervised speech model in a perceptionexperiment (ABX discrimination task). Although the ABXtask has been used for acoustic model evaluation in previousresearch, the results have not, until now, been compared di-rectly with human behaviour in an experiment. We show that astandard, well-performing model (DPGMM) has better accu-racy at predicting human responses than the acoustic baseline.The model also shows a native language effect, better resem-bling native listeners of the language on which it was trained.However, the native language effect shown by the models isdifferent than the one shown by the human listeners, and, no-tably, the models do not show the same overall patterns ofvowel confusions.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"linguistics; language acquisition; machine learn-ing; speech recognition"}],"section":"Papers with Poster Presentations","is_remote":true,"remote_url":"https://escholarship.org/uc/item/1tj9z2kv","frozenauthors":[{"first_name":"Juliette","middle_name":"","last_name":"Millet","name_suffix":"","institution":"Universit ́e Paris Diderot","department":""},{"first_name":"Nika","middle_name":"","last_name":"Jurov","name_suffix":"","institution":"Universit ́e Paris Diderot","department":""},{"first_name":"Ewan","middle_name":"","last_name":"Dunbar","name_suffix":"","institution":"Universit ́e Paris Diderot","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2019-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/28813/galley/18684/download/"}]}