This study aimed to apply Speech to Text Recognition (STR) for individual oral presentations and group discussions of students in a synchronous cyber classroom. An experiment was conducted to analyze the effectiveness of applying STR on learning performance. Students' perceptions and behavioral intentions toward using STR were also investigated. The results revealed students of the experimental group performed significantly better compared to students of the control group in writing essays, intermediate test and post-test. In addition, students perceived the STR was easy to use and useful for learning. Most of the students expressed that they are willing to use the STR for learning in the future. The results of this study showed that the STR is beneficial to students' oral presentations and group discussions in a synchronous cyber classroom so as to improve their overall learning achievement.

This paper presents a query processing strategy for the content-based video query language named CVQL. By CVQL, users can flexibly specify query predicates by the spatial and temporal relationships of the content objects. The query processing strategy evaluates the predicates and returns qualified videos or frames as results. Before the evaluation of the predicates, a preprocessing is performed to avoid unnecessary accessing of videos which are impossible to be the answers. The preprocessing checks the existence of the content objects specified in the predicates to eliminate unqualified videos. For the evaluation of the predicates, an M-index is designed based on the analysis of the behaviors of the content objects. The M-index is employed to avoid frame-by-frame evaluation of the predicates. Experimental results are presented to illustrate the performance of this approach.