# Preserving Phonemic Distinctions for Ordinal Regression: A Novel Loss Function for Automatic Pronunciation Assessment

arXiv: https://arxiv.org/abs/2310.01839 · HTML: https://mlsanity.com/paper/2310.01839/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 28 references that are in the map.
- First posted on arXiv 3 Oct 2023.

## Builds on (most cited first, 12 of 12)

- [speechocean762: An Open-Source Non-native English Speech Corpus For Pronunciation Assessment](https://mlsanity.com/paper/2104.01378/) (2021)
- [Transformer-Based Multi-Aspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment](https://mlsanity.com/paper/2205.03432/) (2022)
- [Context-aware Goodness of Pronunciation for Computer-Assisted Pronunciation Training](https://mlsanity.com/paper/2008.08647/) (2020)
- [3M: An Effective Multi-view, Multi-granularity, and Multi-aspect Modeling Approach to English Pronunciation Assessment](https://mlsanity.com/paper/2208.09110/) (2022)
- [Hierarchical Pronunciation Assessment with Multi-Aspect Attention](https://mlsanity.com/paper/2211.08102/) (2022)
- [Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention](https://mlsanity.com/paper/2012.14788/) (2020)
- [An ASR-free Fluency Scoring Approach with Self-Supervised Learning](https://mlsanity.com/paper/2302.09928/) (2023)
- [Text-Conditioned Transformer for Automatic Pronunciation Error Detection](https://mlsanity.com/paper/2008.12424/) (2020)
- [Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need](https://mlsanity.com/paper/2207.00774/) (2022)
- [L2 proficiency assessment using self-supervised speech representations](https://mlsanity.com/paper/2211.08849/) (2022)
- [Score-balanced Loss for Multi-aspect Pronunciation Assessment](https://mlsanity.com/paper/2305.16664/) (2023)
- [End-to-End Word-Level Pronunciation Assessment with MASK Pre-training](https://mlsanity.com/paper/2306.02682/) (2023)

## Built on by (most cited first, 3 of 3)

- [JCAPT: A Joint Modeling Approach for CAPT](https://mlsanity.com/paper/2506.19315/) (2025)
- [Multi-task Pretraining for Enhancing Interpretable L2 Pronunciation Assessment](https://mlsanity.com/paper/2509.16876/) (2025)
- [MuFFIN: Multifaceted Pronunciation Feedback Model with Interactive Hierarchical Neural Modeling](https://mlsanity.com/paper/2510.04956/) (2025)

## Abstract (arXiv)

Automatic pronunciation assessment (APA) manages to quantify the pronunciation proficiency of a second language (L2) learner in a language. Prevailing approaches to APA normally leverage neural models trained with a regression loss function, such as the mean-squared error (MSE) loss, for proficiency level prediction. Despite most regression models can effectively capture the ordinality of proficiency levels in the feature space, they are confronted with a primary obstacle that different phoneme categories with the same proficiency level are inevitably forced to be close to each other, retaining less phoneme-discriminative information. On account of this, we devise a phonemic contrast ordinal (PCO) loss for training regression-based APA models, which aims to preserve better phonemic distinctions between phoneme categories meanwhile considering ordinal relationships of the regression target output. Specifically, we introduce a phoneme-distinct regularizer into the MSE loss, which encourages feature representations of different phoneme categories to be far apart while simultaneously pulling closer the representations belonging to the same phoneme category by means of weighted distances. An extensive set of experiments carried out on the speechocean762 benchmark dataset suggest the feasibility and effectiveness of our model in relation to some existing state-of-the-art models.