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

arXiv: https://arxiv.org/abs/2101.06396 · HTML: https://mlsanity.com/paper/2101.06396/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 16 Jan 2021.

## Builds on (most cited first, 6 of 6)

- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems](https://mlsanity.com/paper/1512.01274/) (2015)
- [ASR-Free Pronunciation Assessment](https://mlsanity.com/paper/2005.11902/) (2020)

## Built on by (most cited first, 5 of 5)

- [Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment](https://mlsanity.com/paper/2502.07029/) (2025)
- [Weakly-supervised word-level pronunciation error detection in non-native English speech](https://mlsanity.com/paper/2106.03494/) (2021)
- [Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need](https://mlsanity.com/paper/2207.00774/) (2022)
- [Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition](https://mlsanity.com/paper/2306.02534/) (2023)
- [Dhvani: A Weakly-supervised Phonemic Error Detection and Personalized Feedback System for Hindi](https://mlsanity.com/paper/2506.02166/) (2025)

## Abstract (arXiv)

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.