Allan Knight

Fast Caption Alignment for Automatic Indexing of Audio

For large archives of audio media, just as with text archives, indexing is important for allowing quick and accurate searches. Similar to text archives, audio archives can use text for indexing. Generating this text requires using transcripts of the spoken portions of the audio. From them, an alignment can be made that allows users to search for specific content and immediately view the content at the position where the search terms were spoken. Although previous research has addressed this issue, the solutions align the transcripts only in real-time or greater. In this paper, the authors propose AutoCap. It is capable of producing accurate audio indexes in faster than real-time for archived audio and in real-time for live audio. In most cases it takes less than one quarter the original duration for archived audio. This paper discusses the architecture and evaluation of the AutoCap project as well as two of its applications.

Effects of Instructor Engagement on Student Use of a Course Management System

College campuses are rapidly adopting Course Management Systems (CMS) such as Moodle and Sakai for undergraduate instruction. These online support systems offer the potential to extend student-instructor interaction beyond the classroom, yet little is known about the effects of instructor engagement on student use.This study evaluates the extent to which instructor use of a CMS affects student use and whether increased student use results in improved academic performance. Participants in two intact courses taught by the same instructor used course resources available on Moodle during an academic quarter. Levels of online course support provided by the instructor were compared with levels of student use. Levels of student use were then compared with academic performance. In this study, we hypothesize that instructor engagement with a CMS affects how students use the system and that this use relates to academic performance.