Improving Cross-Lingual Phonetic Representation of Low-Resource Languages Through Language Similarity Analysis

TL;DR

This study analyzes how linguistic similarity influences cross-lingual phonetic representations in low-resource languages, demonstrating that phonological proximity significantly improves speech recognition performance.

Contribution

It introduces a detailed phonetic similarity assessment method and shows how language selection based on phonological proximity enhances cross-lingual speech processing.

Findings

Phonologically similar languages improve recognition accuracy by 55.6%.

Higher phonological similarity within language families boosts performance.

Using phonologically similar languages can outperform large-scale self-supervised models.

Abstract

This paper examines how linguistic similarity affects cross-lingual phonetic representation in speech processing for low-resource languages, emphasizing effective source language selection. Previous cross-lingual research has used various source languages to enhance performance for the target low-resource language without thorough consideration of selection. Our study stands out by providing an in-depth analysis of language selection, supported by a practical approach to assess phonetic proximity among multiple language families. We investigate how within-family similarity impacts performance in multilingual training, which aids in understanding language dynamics. We also evaluate the effect of using phonologically similar languages, regardless of family. For the phoneme recognition task, utilizing phonologically similar languages consistently achieves a relative improvement of 55.6% over monolingual training, even surpassing the performance of a large-scale self-supervised learning model. Multilingual training within the same language family demonstrates that higher phonological similarity enhances performance, while lower similarity results in degraded performance compared to monolingual training.