Comparison of L2 Korean pronunciation error patterns from five L1 backgrounds by using automatic phonetic transcription

TL;DR

This study analyzes pronunciation errors of L2 Korean by speakers from five different L1 backgrounds using automatic phonetic transcription, identifying common and language-specific error patterns.

Contribution

It introduces a large-scale, automated method for comparing L2 Korean pronunciation errors across multiple L1 backgrounds using phonetic transcription and confusion matrices.

Findings

Common errors include substitution of aspirated consonants and deletion of final consonants.

Language-specific errors such as /l/ to /n/ substitution in Vietnamese.

Identification of 39 unique error patterns across different L1 backgrounds.

Abstract

This paper presents a large-scale analysis of L2 Korean pronunciation error patterns from five different language backgrounds, Chinese, Vietnamese, Japanese, Thai, and English, by using automatic phonetic transcription. For the analysis, confusion matrices are generated for each L1, by aligning canonical phone sequences and automatically transcribed phone sequences obtained from fine-tuned Wav2Vec2 XLS-R phone recognizer. Each value in the confusion matrices is compared to capture frequent common error patterns and to specify patterns unique to a certain language background. Using the Foreign Speakers' Voice Data of Korean for Artificial Intelligence Learning dataset, common error pattern types are found to be (1) substitutions of aspirated or tense consonants with plain consonants, (2) deletions of syllable-final consonants, and (3) substitutions of diphthongs with monophthongs. On the other hand, thirty-nine patterns including (1) syllable-final /l/ substitutions with /n/ for Vietnamese and (2) /\textturnm/ insertions for Japanese are discovered as language-dependent.