Evaluating automatic speech recognition systems as quantitative models of cross-lingual phonetic category perception

Thomas Schatz 1 Francis Bach 2, 3 Emmanuel Dupoux 1, 4
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
4 CoML - Apprentissage machine et développement cognitif
LSCP - Laboratoire de sciences cognitives et psycholinguistique, Inria de Paris
Abstract : Theories of cross-linguistic phonetic category perception posit that listeners perceive foreign sounds by mapping them onto their native phonetic categories, but, until now, no way to effectively implement this mapping has been proposed. In this paper, Automatic Speech Recognition systems trained on continuous speech corpora are used to provide a fully specified mapping between foreign sounds and native categories. The authors show how the machine ABX evaluation method can be used to compare predictions from the resulting quantitative models with empirically attested effects in human cross-linguistic phonetic category perception.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01888735
Contributor : Emmanuel Dupoux <>
Submitted on : Friday, December 7, 2018 - 2:57:22 PM
Last modification on : Thursday, February 7, 2019 - 5:19:46 PM
Long-term archiving on : Friday, March 8, 2019 - 2:45:55 PM

File

Schatz_BD_2018_Quantitative_mo...
Files produced by the author(s)

Identifiers

Collections

Citation

Thomas Schatz, Francis Bach, Emmanuel Dupoux. Evaluating automatic speech recognition systems as quantitative models of cross-lingual phonetic category perception. Journal of the Acoustical Society of America, Acoustical Society of America, 2018, 143 (5), pp.EL372 - EL378. ⟨10.1121/1.5037615⟩. ⟨hal-01888735⟩

Share

Metrics

Record views

84

Files downloads

47