[
    {
        "id": "osp-17475",
        "type": "article-journal",
        "title": "Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language Identification",
        "author": [
            {
                "family": "Kim",
                "given": "Minu"
            },
            {
                "family": "Lee",
                "given": "Jihwan"
            },
            {
                "family": "Mortensen",
                "given": "David R."
            },
            {
                "family": "Narayanan",
                "given": "Shrikanth"
            }
        ],
        "URL": "https://omanscience.com/en/articles/mitigating-accent-language-confusion-in-self-supervised-speech-representations-for-language-identification",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "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."
    }
]