Audio scene segmentation for video with generic content

Feng Niu, Naveen Goela, Ajay Divakaran, Mohamed Abdel-Mottaleb

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Scopus citations


In this paper, we present a content-adaptive audio texture based method to segment video into audio scenes. The audio scene is modeled as a semantically consistent chunk of audio data. Our algorithm is based on "semantic audio texture analysis." At first, we train GMM models for basic audio classes such as speech, music, etc. Then we define the semantic audio texture based on those classes. We study and present two types of scene changes, those corresponding to an overall audio texture change and those corresponding to a special "transition marker" used by the content creator, such as a short stretch of music in a sitcom or silence in dramatic content. Unlike prior work using genre specific heuristics, such as some methods presented for detecting commercials, we adaptively find out if such special transition markers are being used and if so, which of the base classes are being used as markers without any prior knowledge about the content. Our experimental results show that our proposed audio scene segmentation works well across a wide variety of broadcast content genres.

Original languageEnglish (US)
Title of host publicationProceedings of SPIE-IS and T Electronic Imaging - Multimedia Content Access
Subtitle of host publicationAlgorithms and Systems II
StatePublished - May 15 2008
EventMultimedia Content Access: Algorithms and Systems II - San Jose, CA, United States
Duration: Jan 30 2008Jan 31 2008

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X


OtherMultimedia Content Access: Algorithms and Systems II
Country/TerritoryUnited States
CitySan Jose, CA


  • Audio scene
  • Segmentation
  • Semantic texture
  • SVM

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics


Dive into the research topics of 'Audio scene segmentation for video with generic content'. Together they form a unique fingerprint.

Cite this