Browsing within Lecture Videos Based on the Chain Index of Speech Transcription

Repp, Stephan; Groß, Andreas; Meinel, Christoph

doi:10.1109/tlt.2008.22

Cited by 49 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional video retrieval based on a feature extraction can not be efficiently applied to e-learning applications due to the unstructured and linear features of lecture videos [5]. For an effective content-based retrieval of the appropriate information in such e-learning applications, it is desirable to have a systematic indexing which can be achieved by an efficient video segmentation algorithm.…”

Section: Related Workmentioning

confidence: 99%

TRACE: Linguistic-Based Approach for Automatic Lecture Video Segmentation Leveraging Wikipedia Texts

Shah

Shaikh

et al. 2015

2015 IEEE International Symposium on Multimedia (ISM)

View full text Add to dashboard Cite

In multimedia-based e-learning systems, the accessibility and searchability of most lecture video content is still insufficient due to the unscripted and spontaneous speech of the speakers. Moreover, this problem becomes even more challenging when the quality of such lecture videos is not sufficiently high. To extract the structural knowledge of a multi-topic lecture video and thus make it easily accessible it is very desirable to divide each video into shorter clips by performing an automatic topic-wise video segmentation. To this end, this paper presents the TRACE system to automatically perform such a segmentation based on a linguistic approach using Wikipedia texts. TRACE has two main contributions: (i) the extraction of a novel linguistic-based Wikipedia feature to segment lecture videos efficiently, and (ii) the investigation of the late fusion of video segmentation results derived from state-of-the-art algorithms. Specifically for the late fusion, we combine confidence scores produced by the models constructed from visual, transcriptional, and Wikipedia features. According to our experiments on lecture videos from VideoLectures.NET and NPTEL 1 , the proposed algorithm segments knowledge structures more accurately compared to existing state-of-theart algorithms. The evaluation results are very encouraging and thus confirm the effectiveness of TRACE.

show abstract

Section: Related Workmentioning

confidence: 99%

TRACE: Linguistic-Based Approach for Automatic Lecture Video Segmentation Leveraging Wikipedia Texts

Shah

Shaikh

et al. 2015

2015 IEEE International Symposium on Multimedia (ISM)

View full text Add to dashboard Cite

show abstract

“…Müller et al [16] focused on automated authoring and retrieval of lecture videos. Repp et al [17] automated the indexing process of stored lecture videos in order to ease content based browsing. Adcock et al [18] created a searchable text index of the slides from publicly available lectures videos.…”

Section: ) Automated Video Capturementioning

confidence: 99%

Moderated Group Authoring System for Campus-Wide Workgroups

Chandra

2012

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Abstract-The ability of lecture videos to capture the different modalities of a class interaction make them a good review tool. Multimedia capable devices are ubiquitous among contemporary students. Many lecturers are leveraging this popularity by distributing videos of lectures. They depend on the university to provide the video capture infrastructure. Some universities use trained videographers. Though they produce excellent videos, these efforts are expensive. Several research projects automate the video capture. However, these research prototypes are not readily deployable because of organizational constraints. Rather than waiting for the university to provide the necessary infrastructure, we show that instructors can personally capture the lecture videos using off-the-shelf components. Consumer grade high definition cameras and powerful personal computers allow instructor captured lecture videos to be as effective as the ones captured by the university. However, instructors will need to spend their own time on the various steps of the video capture workflow. They are also untrained in media capture; the capture mechanisms must be simple. Based on our experience in capturing lecture videos over three and a half years, we describe the technical challenges encountered in this endeavor. For instructors who accept the educational value of distributing lecture videos, we show that the effort required to capture and process the videos was modest. However, most existing campus storage and distribution options are unsuitable for the resource demands imposed by video distribution. We describe the strengths of several viable distribution alternatives. The instructors should work with the campus information technology personnel and design a distribution mechanism that considers the network location of the students.

show abstract

“…developed a browsing-system based on the keywords in the lectures. They used a chain-index for dissolving word disambiguation and supported a webinterface for the learners [15]. But little information can be found in the literature about educational systems that use a semantic search engine for finding additional (semantic) information effectively in a knowledge base of recorded lectures.…”

Section: Related Workmentioning

confidence: 99%

Automatic Extraction of Semantic Descriptions from the Lecturer's Speech

Repp

Meinel

2009

2009 IEEE International Conference on Semantic Computing

View full text Add to dashboard Cite

The number of digital lecture video recordings has increased dramatically since recording technology became easier to use. The accessibility and ability to search within this large archive are limited and difficult. Manual annotation is time-consuming and therefore useless. A promising approach is based on using the audio layer of a lecture recording to obtain semantic information about the lecture's contents. The speech transcript and the words from the power point slides are sufficient to generate semantic metadata serialized in an OWL file. Two annotation methods are discussed, evaluated and compared to each other and to a perfectly annotated OWL file, as well as to an annotation based on a corrected transcript of the lecture.

show abstract

Browsing within Lecture Videos Based on the Chain Index of Speech Transcription

Cited by 49 publications

References 33 publications

TRACE: Linguistic-Based Approach for Automatic Lecture Video Segmentation Leveraging Wikipedia Texts

TRACE: Linguistic-Based Approach for Automatic Lecture Video Segmentation Leveraging Wikipedia Texts

Moderated Group Authoring System for Campus-Wide Workgroups

Automatic Extraction of Semantic Descriptions from the Lecturer's Speech

Contact Info

Product

Resources

About