Sorry, you need to enable JavaScript to visit this website.

Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling

Citation Author(s):
Daniel Korzekwa, Jaime Lorenzo-Trueba, Szymon Zaporowski, Shira Calamaro, Thomas Drugman, Bozena Kostek
Submitted by:
Daniel Korzekwa
Last updated:
25 June 2021 - 8:23am
Document Type:
Presentation Slides
Document Year:
Presenters Name:
Daniel Korzekwa



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.

0 users have voted:

Dataset Files