aalto1 untyped-item.component.html

Automated content assessment and feedback for Finnish L2 learners in a picture description speaking task

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

Proceedings of the Interspeech 2024, pp. 317-321, Proceedings of the Annual Conference of the International Speech Communication Association

Abstract

We propose a framework to address several unsolved challenges in second language (L2) automatic speaking assessment (ASA) and feedback. The challenges include: 1. ASA of visual task completion, 2. automated content grading and explanation of spontaneous L2 speech, 3. corrective feedback generation for L2 learners, and 4. all the above for a language that has minimal speech data of L2 learners. The proposed solution combines visual natural language generation (NLG), automatic speech recognition (ASR) and prompting a large language model (LLM) for low-resource L2 learners. We describe the solution and the outcomes of our case study for a picture description task in Finnish. Our results indicate substantial agreement with human experts in grading, explanation and feedback. This framework has the potential for a significant impact in constructing next-generation computer-assisted language learning systems to provide automatic scoring with feedback for learners of low-resource languages.

Description

Other note

Citation

Phan, N, von Zansen, A, Kautonen, M, Voskoboinik, E, Grosz, T, Hilden, R & Kurimo, M 2024, Automated content assessment and feedback for Finnish L2 learners in a picture description speaking task. in Proceedings of the Interspeech 2024. Proceedings of the Annual Conference of the International Speech Communication Association, International Speech Communication Association (ISCA), pp. 317-321, Interspeech, Kos Island, Greece, 01/09/2024. https://doi.org/10.21437/interspeech.2024-1166

Endorsement

Review

Supplemented By

Referenced By