Recent advancements in machine learning have significantly improved speech recognition, but recognizing speech from non-fluent or accented speakers remains a challenge. Previous efforts, relying on rule-based pronunciation patterns, have struggled to fully capture non-native errors. We propose two data-driven approaches using speech corpora to automatically detect mispronunciation patterns. By aligning non-native phones with their native counterparts using attention maps, we achieved a 5.7% improvement in speech recognition on native English datasets and a 12.8% improvement for non-native English speakers, particularly Korean speakers. Our method offers practical advancements for robust Automatic Speech Recognition (ASR) systems particularly for situations where prior linguistic knowledge is not applicable.
@article{arxiv.2502.00583,
title = {Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition},
author = {Anna Seo Gyeong Choi and Jonghyeon Park and Myungwoo Oh},
journal= {arXiv preprint arXiv:2502.00583},
year = {2025}
}