Search for: All records

Speech recognition is very challenging in student learning environments that are characterized by significant cross-talk and background noise. To address this problem, we present a bilingual speech recognition system that uses an interactive video analysis system to estimate the 3D speaker geometry for realistic audio simulations. We demonstrate the use of our system in generating a complex audio dataset that contains significant cross-talk and background noise that approximate real-life classroom recordings. We then test our proposed system with real-life recordings. In terms of the distance of the speakers from the microphone, our interactive video analysis system obtained a better average error rate of 10.83% compared to 33.12% for a baseline approach. Our proposed system gave an accuracy of 27.92% that is 1.5% better than Google Speech-to-text on the same dataset. In terms of 9 important keywords, our approach gave an average sensitivity of 38% compared to 24% for Google Speech-to-text, while both methods maintained high average specificity of 90% and 92%. On average, sensitivity improved from 24% to 38% for our proposed approach. On the other hand, specificity remained high for both methods (90% to 92%). 

Background - One of the most critical challenges in engineering education is improving students’ divergent thinking skills. Usually, we observe students’ fixating on only one single solution for engineering problems. However, their ability to think outside the box and provide alternative solutions should be developed. Research shows that engagement may foster the development of thoughts and boost creativity. Purpose/Hypothesis – Our aim was to investigate students’ engagement with tasks that inspire different facets of creativity (verbal, numeric, and visual). Considering the role of demographics in student engagement, we explored the relationship between their engagement level and demographic traits such as gender, major, age, grades (GPA), and the languages they know besides their native tongue. Design/Method - We utilized electrodermal activity (EDA) sensors, a well-documented proxy of emotional engagement, to measure students’ engagement level while performing tasks that inspire different facets of creativity (verbal, numeric, and visual). Due to the non-normal distribution of the data, non-parametric statistical tests were conducted considering engagement as a dependent variable and demographic traits as independent variables. Results - Statistically significant differences in students’ engagement when exposed to creativity inspired tasks were observed. However, no association between demographics and engagement levels were detected. Conclusions - The results of the study may support educators in designing the instructional materials considering creativity-inspired activities so that students’ engagement level can be increased. Further, results from this study can inform experimental designs, specifically participant selection, in engagement focused studies.