# Maximum F1-score training for end-to-end mispronunciation detection and diagnosis of L2 English speech

arXiv: https://arxiv.org/abs/2108.13816 · HTML: https://mlsanity.com/paper/2108.13816/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Aug 2021.

## Built on by (most cited first, 4 of 4)

- [Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need](https://mlsanity.com/paper/2207.00774/) (2022)
- [Reformulating van Rijsbergen's Fβ metric for weighted binary cross-entropy](https://mlsanity.com/paper/2210.16458/) (2022)
- [Predicting Mortality and Functional Status Scores of Traumatic Brain Injury Patients using Supervised Machine Learning](https://mlsanity.com/paper/2410.20300/) (2024)
- [Domain-Aware Mispronunciation Detection and Diagnosis Using Language-Specific Statistical Graphs](https://mlsanity.com/paper/2606.05569/) (2026)

## Abstract (arXiv)

End-to-end (E2E) neural models are increasingly attracting attention as a promising modeling approach for mispronunciation detection and diagnosis (MDD). Typically, these models are trained by optimizing a cross-entropy criterion, which corresponds to improving the log-likelihood of the training data. However, there is a discrepancy between the objectives of model training and the MDD evaluation, since the performance of an MDD model is commonly evaluated in terms of F1-score instead of phone or word error rate (PER/WER). In view of this, we in this paper explore the use of a discriminative objective function for training E2E MDD models, which aims to maximize the expected F1-score directly. A series of experiments conducted on the L2-ARCTIC dataset show that our proposed method can yield considerable performance improvements in relation to some state-of-the-art E2E MDD approaches and the celebrated GOP method.