Audiovisual Summarization of Lectures and Meetings Using a Segment Similarity Graph

We propose a method for extractive summarization of audiovisual recordings focusing on topic-level segments. We first build a content similarity graph between all segments across the collection, using word vectors from the transcripts, and then select the most central segments for the summaries. We evaluate the method quantitatively on the AMI Meeting Corpus using gold standard reference summaries and the Rouge metric, and qualitatively on lecture recordings using a novel two-tiered approach with human judges. The results show that our method compares favorably with others in terms of Rouge, and outperforms the baselines for human scores, thus also validating our evaluation protocol.

Presented at:
ACM - Proceedings of the ACM International Conference on Multimedia Retrieval (ICMR), New York, NY
ACM Press

 Record created 2016-04-19, last modified 2018-09-13

Rate this document:

Rate this document:
(Not yet reviewed)