Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech

Daniel Korzekwa; Jaime Lorenzo-trueba; Thomas Drugman; Shira Calamaro; Bożena Kostek

doi:10.21437/interspeech.2021-38

Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech

Abstrakt

We propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced L2 speech, the model is more likely to overfit. To limit this risk, we train it in a multi-task setup. In the first task, we estimate the probabilities of word-level mispronunciation. For the second task, we use a phoneme recognizer trained on phonetically transcribed L1 speech that is easily accessible and can be automatically annotated. Compared to state-of-the-art approaches, we improve the accuracy of detecting word-level pronunciation errors in AUC metric by 30% on the GUT Isle Corpus of L2 Polish speakers, and by 21.5% on the Isle Corpus of L2 German and Italian speakers

Cytowania

1 0

CrossRef
0

Web of Science
8

Scopus

Autorzy (5)

Daniel Korzekwa mgr inż.
Jaime Lorenzo-trueba
Thomas Drugman dr
Shira Calamaro
Bożena Kostek prof. dr hab. inż.
- Wydział Elektroniki, Telekomunikacji i Informatyki
- Politechnika Gdańska

Cytuj jako

Pełna treść

pobierz publikację

pobrano 44 razy

Wersja publikacji: Accepted albo Published Version
DOI:: Cyfrowy identyfikator dokumentu elektronicznego (otwiera się w nowej karcie) 10.21437/Interspeech.2021-38
Licencja: Copyright (2021 ISCA)

Słowa kluczowe

AUTOMATED PRONUNCIATION ASSESSMENT, SPEECH PROCESSING, SECOND-LANGUAGE LEARNING, DEEP LEARNING

Informacje szczegółowe

Kategoria:

Aktywność konferencyjna

Typ:

publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)

Język:

angielski

Rok wydania:

2021

Opis bibliograficzny:

Korzekwa D., Lorenzo-Trueba J., Drugman T., Calamaro S., Kostek B.: Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech// / : , 2021,

DOI: