• Journal of Information Technology Services
• /
• v.20 no.4
• /
• pp.129-140
• /
• 2021

Recently, interest in AI tutors is rising as a way to bridge the educational gap in school settings. However, research confirming the effectiveness of AI tutors is lacking. The purpose of this study is to explore how effective learner characteristics and recommended item learning activities are in predicting learner's academic performance in an adaptive online learning environment. This study proposed the hypothesis that learner characteristics (prior knowledge, midterm evaluation) and recommended item learning activities (learning time, correct answer check, incorrect answer correction, satisfaction, correct answer rate) predict academic achievement. In order to verify the hypothesis, the data of 362 learners were analyzed by collecting data from the learning management system (LMS) from the perspective of learning analytics. For data analysis, regression analysis was performed using the regsubset function provided by the leaps package of the R program. The results of analyses showed that prior knowledge, midterm evaluation, correct answer confirmation, incorrect answer correction, and satisfaction had a positive effect on academic performance, but learning time had a negative effect on academic performance. On the other hand, the percentage of correct answers did not have a significant effect on academic performance. The results of this study suggest that recommended item learning activities, which mean behavioral indicators of interaction with AI tutors, are important in the learning process stage to increase academic performance in an adaptive online learning environment.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.