Abstract
Spoken language identification (LID) aims to recognize the target language regardless of accent. In practice, however, LID models fine-tuned from self-supervised speech representations frequently confuse accents with languages, misclassifying non-native (L2) speech as the speaker's first language (L1). We show that non-native speech representations lie between native target-language and native L1 poles, causing systematic misclassification. To address this, we introduce a geometric projection that estimates an L1-bias direction solely from native speech and removes it before the frozen LID head. Across five MMS-LID models and non-native corpora, this projection substantially improves target language identification for L2-accented speech while preserving predictions for native speech. These results show that accent-induced L1 bias can be corrected directly within the representation space without L2 training data or model adaptation.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kim, M., Lee, J., Mortensen, D. R., & Narayanan, S. (2026). Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification. https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification
MLA 9
Kim, Minu, et al. "Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification." https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification.
Chicago (author–date)
Kim, Minu, Jihwan Lee, David R. Mortensen, and Shrikanth Narayanan. 2026. "Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification." https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification.
Harvard
Kim, M., Lee, J., Mortensen, D. R. and Narayanan, S. (2026) 'Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification', Available at: https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification.
Vancouver
Kim M, Lee J, Mortensen DR, Narayanan S. Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification. https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification
IEEE
M. Kim, J. Lee, D. R. Mortensen, and S. Narayanan, "Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification," https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification.