Veronika Kritskaia

Veronika Kritskaia

Auto-generated profile, based on publicly available information

Veronika Kritskaia

Department of Cognitive Science and Artificial Intelligence Tilburg University Tilburg Netherlands

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 August 2024 in Journal of Computer Assisted Learning
Verified
Journal Article
Open access
LDLaduona Dai
Laduona Dai
VKVeronika Kritskaia
Veronika Kritskaia
EVEvelien van der Velden
Evelien van der Velden
RVReinder Vervoort
Reinder Vervoort
MBMarlieke Blankendaal
Marlieke Blankendaal
MLMax M. Louwerse
Max M. Louwerse
Background: The integration of Text‐to‐Speech (TTS) and virtual reality (VR) technologies in K‐12 education is an emerging trend. However, little is known about how students perceive these technologies and whether these technologies effectively facilitate learning. Objectives: This study aims to investigate the perception and effectiveness of TTS voices and VR agents in a K‐12 classroom setting, with a focus on information recall. Methods: Using a recent TTS architecture, we developed four different synthetic voices based on 5, 10, 15 and 20 h of training materials. Two experiments were conducted involving students in a K‐12 setting. The first experiment examined students' evaluations of TTS voices with varying hours of training material and the impact on information recall. The second experiment assessed the effect of pairing TTS voices with a VR agent on students' perception and recall performance. Results and Conclusions: Human voices received superior quality ratings over TTS voices within the classroom context. The integration of a VR agent was found to enhance the perception of TTS voices, aligning with existing literature on the positive impact of virtual agents on speech synthesis. However, this incorporation did not translate to improved recall, suggesting that the student focus may have been compromised by the VR agent's novelty and its design limitations.

21 November 2022
Verified
Conference Paper
Open access
LDLaduona Dai
Laduona Dai
VKVeronika Kritskaia
Veronika Kritskaia
EVEvelien van der Velden
Evelien van der Velden
MJMerel Jung
Merel Jung
MPMarie Postma
Marie Postma
MLMax M. Louwerse
Max M. Louwerse
With increased interest in the use of virtual avatars for educational purposes, there is a growing need for high-quality text-to-speech solutions. However, the effects of using synthesized speech in educational applications for younger listeners are still unclear as past findings have been inconsistent and most of them have been obtained in a lab setting with adult assessors. Next to that, it is unclear how much training material is needed for high quality speech synthesis. Particularly for low resource languages, the assumption that good quality synthesized speech requires substantial amounts of vocal recordings to train may be hindering the development of TTS-based solutions. In this study, we created four Dutch text-to-speech (TTS) models from different amounts of training material and evaluated the models in terms of voice perception and recall with K12 students in a classroom environment. Results showed that while the original human voice outperformed the synthesized voices in terms of the listening experience and knowledge test score, more hours of training material did not necessarily result in better outcomes suggesting that 10-15 hours of speech material might be sufficient for training a Dutch TTS. A weak positive correlation was found between listening experience and knowledge test performance, with the low listening effort being the most important factor. This outcome suggests that comprehensibility is likely the most important TTS feature for educational applications.