ABSTRACT
This paper summarizes our contribution to the Yahoo! task of the ACM Multimedia Grand Challenge. This challenge asks for the robust automatic segmentation of videos according to "narrative themes". Based on the automatic segmentation methods presented in [1] and partly [2], we describe a system to navigate Seinfeld episodes based on automatic segmentation of the audio track only. The system distinguishes laughter, music, and other noise as well as speech segments. Speech segments are identified against pre-trained speaker models of the actors. Given this segmentation and the artistic production rules that underlie the genre situation comedy and Seinfeld in particular, the system enables a user to browse an episode by scene, by punchline, and by dialog segments. The themes can be filtered by the main actors, e.g. the user can select to see only punchlines by Jerry and Kramer. Based on the length of the laughter, the top 5 punchlines are also identified and presented to the user.
- G. Friedland and O. Vinyals. Live speaker identification in conversations. In Proceedings of ACM Multimedia, pages 1017--1018. ACM, October 2008. Google ScholarDigital Library
- G. Friedland, C. Yeo, and H. Hung. Visual speaker localization aided by acoustic models. In Proceedings of ACM Multimedia, to appear. ACM, October 2009. Google ScholarDigital Library
Index Terms
- Joke-o-mat: browsing sitcoms punchline by punchline
Recommendations
Joke-o-Mat HD: browsing sitcoms with human derived transcripts
MM '10: Proceedings of the 18th ACM international conference on MultimediaJoke-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 ...
Conversational Agents Replying with a Manzai-style Joke
OzCHI '21: Proceedings of the 33rd Australian Conference on Human-Computer InteractionAutomated conversational agents are becoming popular in various everyday contexts. In order to fulfill a more important role in human society, people would need to feel a sense of familiarity with such agents. To achieve this, we focus on humor, which ...
Different Knowledge, Same Joke: Response-Based Computational Detection of Humor
Proceedings of the Third International Conference on Distributed, Ambient, and Pervasive Interactions - Volume 9189The paper explores the very basis of linguistic theories of humor with a view of applying them to computational humor. Computation requires tighter definitions. The paper analyzes joke-carrying texts based on the existing script-based methods. It ...
Comments