Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition
This provides practical advancements for robust Automatic Speech Recognition systems, particularly for non-native speakers, but is incremental as it builds on existing methods.
The paper tackled the problem of recognizing speech from non-fluent or accented speakers by proposing data-driven approaches to detect mispronunciation patterns, resulting in a 5.7% improvement in speech recognition on native English datasets and a 12.8% improvement for non-native English speakers.
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.