BROWSE
Detail
Conference Paper
Non-Dialog Section Detection of the Media Contents for DVS Authoring
Cited - time in 
Share 
Share
- Authors
- Inseon Jang, ChungHyun Ahn, Younseon Jang
- Issue Date
- 2014-01
- Citation
- International Workshop on Advanced Image Technology (IWAIT) 2014, pp.1-4
- Language
- English
- Type
- Conference Paper
- Abstract
- This paper addresses a problem of non-dialog section detection for the DVS authoring, the goal of which is to discriminate the non-dialog section from the media contents which involve the presence of various sounds. Proposed method jointly exploits the inter-channels structure and each source characteristics of the broadcasting audio whose number of channel is stereo. It provides more accurate detection without training using huge audio DB, which is necessary for conventional speech/non-speech discrimination method, so that it uses less computational resources than other approaches. Experimental results on real media contents show the qualitative superiority of the proposed method.
- KSP Keywords
- Non-speech, Speech discrimination, computational resources, discrimination method, source characteristics