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

TL;DR

This paper introduces an uncertainty-aware model for detecting mispronunciations in non-native English speech, addressing recognition inaccuracies and multiple valid pronunciations to improve detection precision.

Contribution

It presents a novel approach that incorporates uncertainty modeling and multiple pronunciation variants, advancing beyond traditional single-pronunciation recognition methods.

Findings

Up to 18% relative increase in detection precision

Effective handling of pronunciation variability

Improved false alarm reduction

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.