{"ID":2853358,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.16387","arxiv_id":"2510.16387","title":"Probing the Hidden Talent of ASR Foundation Models for L2 English Oral Assessment","abstract":"In this paper, we explore the untapped potential of Whisper, a well-established automatic speech recognition (ASR) foundation model, in the context of L2 spoken language assessment (SLA). Unlike prior studies that extrinsically analyze transcriptions produced by Whisper, our approach goes a step further to probe its latent capabilities by extracting acoustic and linguistic features from hidden representations. With only a lightweight classifier being trained on top of Whisper's intermediate and final outputs, our method achieves strong performance on the GEPT picture-description dataset, outperforming existing cutting-edge baselines, including a multimodal approach. Furthermore, by incorporating image and text-prompt information as auxiliary relevance cues, we demonstrate additional performance gains. Finally, we conduct an in-depth analysis of Whisper's embeddings, which reveals that, even without task-specific fine-tuning, the model intrinsically encodes both ordinal proficiency patterns and semantic aspects of speech, highlighting its potential as a powerful foundation for SLA and other spoken language understanding tasks.","short_abstract":"In this paper, we explore the untapped potential of Whisper, a well-established automatic speech recognition (ASR) foundation model, in the context of L2 spoken language assessment (SLA). Unlike prior studies that extrinsically analyze transcriptions produced by Whisper, our approach goes a step further to probe its la...","url_abs":"https://arxiv.org/abs/2510.16387","url_pdf":"https://arxiv.org/pdf/2510.16387v2","authors":"[\"Fu-An Chao\",\"Bi-Cheng Yan\",\"Berlin Chen\"]","published":"2025-10-18T08:10:24Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.SD\",\"eess.AS\"]","methods":"[]","has_code":false}