The Relevance of Text and Speech Features in Automatic Non-native English Accent Identification

TL;DR

This study demonstrates that native accent identification from non-native English speech can achieve nearly 90% accuracy using simple audio and text features, with speech features offering robustness across prompts.

Contribution

It introduces a low-level feature-based method for accent identification that does not rely on word or phoneme recognition, showing robustness and adaptability across languages.

Findings

Achieved close to 90% classification accuracy.

Speech features are robust to prompt variation.

Character n-grams perform similarly to speech features.

Abstract

This paper describes our experiments with automatically identifying native accents from speech samples of non-native English speakers using low level audio features, and n-gram features from manual transcriptions. Using a publicly available non-native speech corpus and simple audio feature representations that do not perform word/phoneme recognition, we show that it is possible to achieve close to 90% classification accuracy for this task. While character n-grams perform similar to speech features, we show that speech features are not affected by prompt variation, whereas ngrams are. Since the approach followed can be easily adapted to any language provided we have enough training data, we believe these results will provide useful insights for the development of accent recognition systems and for the study of accents in the context of language learning.