Metraipolis › archive › dc_e6b015ff9eb6
CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model — arXiv:2608.13101
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13101
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:24:34.660Z
- SHA-256 of the archived text
4e55da77134b042b5bcc1d6a0eca0bba9e13ea25fbdc14a3cc8e0a9bc733004f- Stable URL of this page
https://metraipolis.com/documento/dc_e6b015ff9eb6
How to cite
CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model — arXiv:2608.13101 — arXiv (en), https://arxiv.org/abs/2608.13101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e6b015ff9eb6 (Metraipolis archive dc_e6b015ff9eb6, sha256 4e55da77134b042b5bcc1d6a0eca0bba9e13ea25fbdc14a3cc8e0a9bc733004f)
BibTeX
@misc{dce6b015ff9eb6,
title = {CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model — arXiv:2608.13101},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13101},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e6b015ff9eb6; sha256 4e55da77134b042b5bcc1d6a0eca0bba9e13ea25fbdc14a3cc8e0a9bc733004f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Research on automatic speaking assessment (ASA) has increasingly adopted multimodal speech large language models to assess learners' speaking performance. However, existing studies provide limited analysis of how acoustic and content information contribute to predictions and how stable the resulting performance is. We propose CASA, a simpler architecture combining Whisper-medium and Qwen3.5-2B that achieves state-of-the-art performance while providing a more interpretable separation between speech delivery and content. On the Speak & Improve Corpus 2025, CASA achieves a root mean square error (RMSE) of 0.358, improving on the previous best RMSE while using approximately half the estimated inference parameters. The general-purpose architecture is designed for adaptation to other ASA corpora without structural changes and relies on three handcrafted fluency features. Through ablations and repeated runs, we analyze the individual and complementary contributions of acoustic and content information, examine performance variability, and demonstrate the potential of large language model reasoning for training-free content validation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CL). Categorie arXiv: Computation and Language (cs.CL) ; Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2608.13101 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:17:42.392Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).