Aaron Earned an Iron Urn: Speech-to-IPA Models Improve Diagnostic of Pronunciation
Data
2023
Tytuł czasopisma
ISSN czasopisma
Tytuł tomu
Wydawca
Wydawnictwo Politechniki Łódzkiej
Lodz University of Technology Press
Lodz University of Technology Press
Abstrakt
Learning the proper pronunciation is one of the key aspects of
foreign language acquisition. Assessment of the correctness of pronunciation
requires the involvement of expert phoneticians and linguists, severely
limiting the scalability of learning solutions. However, the recent adaptation
of the Transformer architecture to the audio domain opens the way for automatic
model-based assessment of pronunciation. In this paper, we present
the pronunciation diagnostic tool developed at PUT and we experimentally
evaluate the correlation between expert human assessment and automatic
model assessment. By combining the Wav2Vec model and the IPA representation,
we prove that pronunciation assessment can be performed automatically
with high precision.
Opis
Słowa kluczowe
Wav2Vec, IPA, pronunciation diagnostic, ASR, Wav2Vec, IPA, diagnostyka wymowy, ASR
Cytowanie
Olejnik F., Stachowiak R., Krysińska I., Morzy M., Aaron Earned an Iron Urn: Speech-to-IPA Models Improve Diagnostic of Pronunciation. W: Progress in Polish Artificial Intelligence Research 4, Wojciechowski A. (Ed.), Lipiński P. (Ed.)., Seria: Monografie Politechniki Łódzkiej Nr. 2437, Wydawnictwo Politechniki Łódzkiej,
Łódź 2023, s. 273-279, ISBN 978-83-66741-92-8, doi: 10.34658/9788366741928.43.