Suryani Binte Atan

Designation
Teaching Fellow

Department
Asian Languages & Cultures (ALC)

Email
[email protected]

SingaKids Pic2Speak: Multilingual AI Tutor – Uplifting Singapore's Bilingual Edge

COPI: Suryani Binte Atan

Duration: 2023 - 2025

Funding Agency: AI Singapore - AI in Education Grand Challenge

Abstract:
We propose SingaKids Pic2Speak – a picture-prompted multilingual virtual tutor for Singaporean students in primary 1 and primary 2 to practice their oral skills in MTL (see Figure 1). In question generation mode, SingaKids Pic2Speak can generate question answer pairs from a picture so teachers can select suitable ones for students to practice. In dialogue mode, these teacher selected question answer pairs can also be used in to prompt students with both the picture and question to elicit spoken answers. SingaKids Pic2Speak will evaluate the student's response in terms of content accuracy, grammatical correctness, and oral delivery (e.g. pronunciation, fluency) and give corresponding feedback. In addition, the engagement level of the student will also be assessed through the speech signal. By considering both engagement and capability, we can preposition recommendations and intervention strategies to increase student learning outcome and interest. The technical challenges...   Show more >



LEARN: Language automated Evaluation by generating Answers / questions from caRtooNs

COPI: Suryani Binte Atan

Duration: 2023 - 2025

Funding Agency: AI Singapore - AI in Education Grand Challenge

Abstract:
This project will address the challenge statement “How can AI enhance the Mother Tongue Language (MTL) learning environment at home for P1 and P2 students to increase oral proficiency by 20% after 2 years”. The proposed solution is to deploy an AI conversational chatbots to practice short, simple conversations with students based on the Picture Description Task. This AI conversational agent will be able to practice spoken exchanges with the student in the MTL. Our novel solution will enable the automatic generation of questions/answers from age-appropriate cartoon images; developing conversation AI chatbots to facilitate data collection, review of generated questions and answers by teachers, student automated assessment; automated recognition of speech from young children in a mixture of English and MTL; and development of automatic picture captioning techniques to extract and match key topics between speech and reference content. The team's key strategy is to first solv...   Show more >



Personalised Adaptive Learning and Assessment System (PALAS)

PI: Suryani Binte Atan

Duration: 2022 - 2023