Digital support for training and assessing second language speaking (DigiTala)
Main funder
Funder's project number: 322965
Funds granted by main funder (€)
- 272 339,00
Funding program
Project timetable
Project start date: 01/09/2019
Project end date: 31/08/2023
Summary
DigiTala will study and develop new revolutionary technology for high-stake oral second language (L2) proficiency assessment, L2 teaching and self-learning. The project aligns different dimensions significant for L2 education (learning, teaching and assessment) and sets out to study the key questions in an interdisciplinary research team. In our pilot tests at upper secondary schools we have collected large digital data which provide a unique opportunity to develop and utilize automatic processing tools such as automatic speech recognition (ASR) and rating to assist in lifting the subjective human assessments to a new level of efficiency and standardization required for performing high-stake assessments. The computerized speech evaluation tools will also be used to concretize the CEFR scales for speaking and to allow new immediate form of feedback in L2 teaching and self-learning. The produced speech and assessment database and tools provide also unique opportunities for researching language proficiency and its human and automatic ratings. In addition to collect valuable research data and advance ASR for language learners, the project will study the phonetic realizations behind the assessment criteria. This is expected to increase the phonetic and articulatory awareness of L2 learners and teachers and innovate new educational methods and materials for L2 teaching. The consortium brings together cutting-edge interdisciplinary expertise for developing effective and reliable tools for computerised recognition and rating of L2 learners’ speech (Kurimo’s team) with a special focus on innovating L2 learning and assessment (Hildén’s team) and research results and networks for L2 learners’ language (Kuronen’s team).
Principal Investigator
Other persons related to this project (JYU)
Primary responsible unit
Follow-up groups
Related publications and other outputs
- Automatic Speaking Assessment of Spontaneous L2 Finnish and Swedish (2023) Al-Ghezi, Ragheb; et al.; A1; OA
- New data, benchmark and baseline for L2 speaking assessment for low-resoure languages (2023) Kurimo, Mikko; et al.; D3; OA
- Prosody and fluency of Finland Swedish as a second language : Investigating global parameters for automated speaking assessment (2023) Kallio, Heini; et al.; A1; OA
- Revising parameters for predicting L2 speech fluency and proficiency (2023) Kallio, Heini; et al.; A4; OA; 978-80-908114-2-3
- Creaky voice and utterance fluency measures in predicting perceived fluency and oral proficiency of spontaneous L2 Finnish (2022) Kallio, Heini; et al.; A4; OA
- Developing Automated Feedback on Spoken Performance : Exploring the Functioning of Five Analytic Rating Scales Using Many-facet Rasch Measurement (2022) Zansen, Anna von; et al.; A4; OA; 978-951-39-9450-1
- Ihmisarvioijien näkemyksiä suullisen kielitaidon automaattisesta arvioinnista, digitaalisesta arviointiprosessista sekä puhesuorituksista arvioitavista ulottuvuuksista (2022) Zansen, Anna von; et al.; A3; OA; 978-951-9388-74-8
- The role of pause location in perceived fluency and proficiency in L2 Finnish (2022) Kallio, Heini; et al.; D3; OA
- Differences in acoustically determined sentence stress between native and L2 speakers of Finland Swedish (2021) Kallio, Heini; et al.; D1; OA
- Kvantitativa perspektiv på L2-tal på olika färdighetsnivåer (2021) Kautonen, Maria; et al.; A1; OA