Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Hong-Yun, Lin, Jhen-Ke, Wang, Chung-Chun, Lu, Hao-Chien, Chen, Berlin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.16025
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918144441843712
author Lin, Hong-Yun
Lin, Jhen-Ke
Wang, Chung-Chun
Lu, Hao-Chien
Chen, Berlin
author_facet Lin, Hong-Yun
Lin, Jhen-Ke
Wang, Chung-Chun
Lu, Hao-Chien
Chen, Berlin
contents Spoken Language Assessment (SLA) estimates a learner's oral proficiency from spontaneous speech. The growing population of L2 English speakers has intensified the demand for reliable SLA, a critical component of Computer Assisted Language Learning (CALL). Existing efforts often rely on cascaded pipelines, which are prone to error propagation, or end-to-end models that often operate on a short audio window, which might miss discourse-level evidence. This paper introduces a novel multimodal foundation model approach that performs session-level evaluation in a single pass. Our approach couples multi-target learning with a frozen, Whisper ASR model-based speech prior for acoustic-aware calibration, allowing for jointly learning holistic and trait-level objectives of SLA without resorting to handcrafted features. By coherently processing the entire response session of an L2 speaker, the model excels at predicting holistic oral proficiency. Experiments conducted on the Speak & Improve benchmark demonstrate that our proposed approach outperforms the previous state-of-the-art cascaded system and exhibits robust cross-part generalization, producing a compact deployable grader that is tailored for CALL applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_16025
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Session-Level Spoken Language Assessment with a Multimodal Foundation Model via Multi-Target Learning
Lin, Hong-Yun
Lin, Jhen-Ke
Wang, Chung-Chun
Lu, Hao-Chien
Chen, Berlin
Computation and Language
Artificial Intelligence
Spoken Language Assessment (SLA) estimates a learner's oral proficiency from spontaneous speech. The growing population of L2 English speakers has intensified the demand for reliable SLA, a critical component of Computer Assisted Language Learning (CALL). Existing efforts often rely on cascaded pipelines, which are prone to error propagation, or end-to-end models that often operate on a short audio window, which might miss discourse-level evidence. This paper introduces a novel multimodal foundation model approach that performs session-level evaluation in a single pass. Our approach couples multi-target learning with a frozen, Whisper ASR model-based speech prior for acoustic-aware calibration, allowing for jointly learning holistic and trait-level objectives of SLA without resorting to handcrafted features. By coherently processing the entire response session of an L2 speaker, the model excels at predicting holistic oral proficiency. Experiments conducted on the Speak & Improve benchmark demonstrate that our proposed approach outperforms the previous state-of-the-art cascaded system and exhibits robust cross-part generalization, producing a compact deployable grader that is tailored for CALL applications.
title Session-Level Spoken Language Assessment with a Multimodal Foundation Model via Multi-Target Learning
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.16025