{"ID":2859675,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04463","arxiv_id":"2510.04463","title":"Evaluating Self-Supervised Speech Models via Text-Based LLMS","abstract":"Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due to the cost of extra training and evaluation. Existing methods for task-agnostic evaluation also require extra training or hyperparameter tuning. We propose a novel evaluation metric using large language models (LLMs). By inputting discrete token sequences and minimal domain cues derived from SSL models into LLMs, we obtain the mean log-likelihood; these cues guide in-context learning, rendering the score more reliable without extra training or hyperparameter tuning. Experimental results show a correlation between LLM-based scores and automatic speech recognition task. Additionally, our findings reveal that LLMs not only functions as an SSL evaluation tools but also provides inference-time embeddings that are useful for speaker verification task.","short_abstract":"Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due to the cost of extra training and evaluation. Existing methods for task-agnosti...","url_abs":"https://arxiv.org/abs/2510.04463","url_pdf":"https://arxiv.org/pdf/2510.04463v1","authors":"[\"Takashi Maekaku\",\"Keita Goto\",\"Jinchuan Tian\",\"Yusuke Shinohara\",\"Shinji Watanabe\"]","published":"2025-10-06T03:25:48Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"eess.AS\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}