Weakly-supervised word-level pronunciation error detection in non-native English speech

TL;DR

This paper introduces a weakly-supervised model for detecting word-level pronunciation errors in non-native English speech, eliminating the need for phonetic transcriptions and improving detection accuracy significantly.

Contribution

It presents a novel multi-task learning approach that leverages phoneme recognizers trained on native speech to detect mispronunciations without detailed phonetic annotations.

Findings

30% improvement in AUC on GUT Isle Corpus for Polish speakers

21.5% improvement in AUC on Isle Corpus for German and Italian speakers

Effective detection of pronunciation errors without phonetic transcriptions

Abstract

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.