Summarising Academic Presentations using Linguistic and Paralinguistic Features

Keith Curtis, Gareth J. F. Jones, Nick Campbell

2018

Abstract

We present a novel method for the automatic generation of video summaries of academic presentations using linguistic and paralinguistic features. Our investigation is based on a corpus of academic conference presentations. Summaries are first generated based on keywords taken from transcripts created using automatic speech recognition (ASR). We augment spoken phrases by incorporating scores for audience engagement, comprehension and speaker emphasis. We evaluate the effectiveness of our summaries generated for individual presentations by performing eye-tracking evaluation of participants as they watch summaries and full presentations, and by questionnaire of participants upon completion of eye-tracking studies. We find that automatically generated summaries tend to maintain the user’s focus and attention for longer, with users losing focus much less often than for full presentations.

Download


Paper Citation


in Harvard Style

Curtis K., Jones G. and Campbell N. (2018). Summarising Academic Presentations using Linguistic and Paralinguistic Features. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 3: HUCAPP; ISBN 978-989-758-288-2, SciTePress, pages 64-73. DOI: 10.5220/0006720500640073


in Bibtex Style

@conference{hucapp18,
author={Keith Curtis and Gareth J. F. Jones and Nick Campbell},
title={Summarising Academic Presentations using Linguistic and Paralinguistic Features},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 3: HUCAPP},
year={2018},
pages={64-73},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006720500640073},
isbn={978-989-758-288-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 3: HUCAPP
TI - Summarising Academic Presentations using Linguistic and Paralinguistic Features
SN - 978-989-758-288-2
AU - Curtis K.
AU - Jones G.
AU - Campbell N.
PY - 2018
SP - 64
EP - 73
DO - 10.5220/0006720500640073
PB - SciTePress