[
    {
        "id": "osp-17484",
        "type": "article-journal",
        "title": "Phoneme-Guided Initialization for LLM-based Speech Recognition",
        "author": [
            {
                "family": "Magoshi",
                "given": "Ryo"
            },
            {
                "family": "Sakai",
                "given": "Shinsuke"
            },
            {
                "family": "Kawahara",
                "given": "Tatsuya"
            }
        ],
        "URL": "https://omanscience.com/en/articles/phoneme-guided-initialization-for-llm-based-speech-recognition",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Speech large language models (speech LLMs) perform well on automatic speech recognition (ASR) when sufficient paired speech-text data is available, but their performance degrades in low-resource settings. A cascaded pipeline that performs speech-to-phoneme (S2P) conversion followed by phoneme-to-grapheme (P2G) conversion has been shown to outperform end-to-end speech LLMs in this regime, suggesting that phoneme-mediated processing is beneficial when paired data is scarce. We propose \\textit{phoneme-guided initialization}, a simple method that uses this insight within an end-to-end framework: we pre-train the audio encoder on S2P and the LLM on P2G tasks, then connect them and fine-tune the full model end-to-end on the target ASR task. Experiments on Japanese (CSJ), Chinese (AISHELL-1), and two low-resource languages from Common Voice 25.0 (Tatar and Urdu) show that our method matches or outperforms both the cascaded S2P-P2G baseline and the end-to-end model without P2G initialization."
    }
]