Joke-o-Mat HD: browsing sitcoms with human derived transcripts

Authors:
Adam Janin;Luke Gottlieb;Gerald Friedland
Affiliations:
International Computer Science Insitute, Berkeley, CA, USA;International Computer Science Insitute, Berkeley, CA, USA;International Computer Science Insitute, Berkeley, CA, USA
Venue:
Proceedings of the international conference on Multimedia
Year:
2010

Citing 5
Cited 4

The SRI-ICSI Spring 2007 Meeting and Lecture Recognition System

Multimodal Technologies for Perception of Humans
Live speaker identification in conversations

MM '08 Proceedings of the 16th ACM international conference on Multimedia
Visual speaker localization aided by acoustic models

MM '09 Proceedings of the 17th ACM international conference on Multimedia
Joke-o-mat: browsing sitcoms punchline by punchline

MM '09 Proceedings of the 17th ACM international conference on Multimedia
Using Artistic Markers and Speaker Identification for Narrative-Theme Navigation of Seinfeld Episodes

ISM '09 Proceedings of the 2009 11th IEEE International Symposium on Multimedia

Swift: reducing the effects of latency in online video scrubbing

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Spoken Content Retrieval: A Survey of Techniques and Technologies

Foundations and Trends in Information Retrieval
Narrative theme navigation for sitcoms supported by fan-generated scripts

Multimedia Tools and Applications
Swifter: improved online video scrubbing

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Joke-o-mat HD is a system that allows a user to navigate sitcoms (such as Seinfeld) by "narrative themes", including scenes, punchlines, and dialog segments. The themes can be filtered by the main actors and by keyword. For example, the user can select to see only punchlines by Kramer that contain the word "armoire". The system infers the narrative themes using segmentation of the audio track into laughter, actors, words, and music. The segmentation can be generated either by an expert annotator, via automatic methods, or by exploiting human derived (HD) "found" data such as fan-generated scripts and closed captions. We demonstrate browsing one episode of Seinfeld using all three methods of generating segmentations.