# Incorporating L2 Phonemes Using Articulatory Features for Robust Speech Recognition

arXiv: https://arxiv.org/abs/2306.02534 · HTML: https://mlsanity.com/paper/2306.02534/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 5 Jun 2023.

## Builds on (most cited first, 9 of 9)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [An End-to-End Mispronunciation Detection System for L2 English Speech Leveraging Novel Anti-Phone Modeling](https://mlsanity.com/paper/2005.11950/) (2020)
- [PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR](https://mlsanity.com/paper/2005.09824/) (2020)
- [Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data](https://mlsanity.com/paper/2205.08014/) (2022)
- [Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning](https://mlsanity.com/paper/2110.00678/) (2021)
- [Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling](https://mlsanity.com/paper/2101.06396/) (2021)
- [Pronunciation Modeling of Foreign Words for Mandarin ASR by Considering the Effect of Language Transfer](https://mlsanity.com/paper/2210.03603/) (2022)

## Built on by (most cited first, 1 of 1)

- [Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition](https://mlsanity.com/paper/2502.00583/) (2025)

## Abstract (arXiv)

The limited availability of non-native speech datasets presents a major challenge in automatic speech recognition (ASR) to narrow the performance gap between native and non-native speakers. To address this, the focus of this study is on the efficient incorporation of the L2 phonemes, which in this work refer to Korean phonemes, through articulatory feature analysis. This not only enables accurate modeling of pronunciation variants but also allows for the utilization of both native Korean and English speech datasets. We employ the lattice-free maximum mutual information (LF-MMI) objective in an end-to-end manner, to train the acoustic model to align and predict one of multiple pronunciation candidates. Experimental results show that the proposed method improves ASR accuracy for Korean L2 speech by training solely on L1 speech data. Furthermore, fine-tuning on L2 speech improves recognition accuracy for both L1 and L2 speech without performance trade-offs.