Search
Abstract
A common approach to the automatic detection of mispronunciation in language learning is to recognize the phonemes produced by a student and compare it to the expected pronunciation of a native speaker. This approach makes two simplifying assumptions: a) phonemes can be recognized from speech with high accuracy, b) there is a single correct way for a sentence to be pronounced. These assumptions do not always hold, which can result in a significant amount of false mispronunciation alarms. We propose a novel approach to overcome this problem based on two principles: a) taking into account uncertainty in the automatic phoneme recognition step, b) accounting for the fact that there may be multiple valid pronunciations. We evaluate the model on non-native (L2) English speech of German, Italian and Polish speakers, where it is shown to increase the precision of detecting mispronunciations by up to 18% (relative) compared to the common approach.
Citations
-
9
CrossRef
-
0
Web of Science
-
1 2
Scopus
Authors (6)
-
Daniel Korzekwa mgr inż.
- Amazon
-
Jaime Lorenzo-trueba
-
Shira Calamaro
-
Thomas Drugman dr
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- publikacja w wydawnictwie zbiorowym recenzowanym (także w materiałach konferencyjnych)
- Language:
- English
- Publication year:
- 2021
- Bibliographic description:
- Korzekwa D., Lorenzo-Trueba J., Zaporowski S., Calamaro S., Drugman T., Kostek B.: Mispronunciation Detection in Non-Native (L2) English with Uncertainty Modeling// / : , 2021,
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/icassp39728.2021.9413953
- Verified by:
- Gdańsk University of Technology
seen 80 times
Recommended for you
Investigating Noise Interference on Speech Towards Applying the Lombard Effect Automatically
- G. Korvel,
- K. Kąkol,
- P. Treigys
- + 1 authors
Introduction to the special issue on machine learning in acoustics
- Z. Michalopoulou,
- P. Gerstoft,
- B. Kostek
- + 1 authors