Classification TV programs based on audio information using hidden Markov model

Zhu Liu, Jincheng Huang, Yao Wang

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

Abstract

This paper describes a technique for classifying TV broadcast video using a hidden Markov model (HMM). Here we consider the problem of discriminating five types of TV programs, namely commercials, basketball games, football games, news reports, and weather forecasts. Eight frame-based audio features are used to characterize the low-level audio properties, and fourteen clip-based audio features are extracted based on these frame-based features to characterize the high-level audio properties. For each type of these five TV programs, we build an ergodic HMM using the clip-based features as observation vectors. The maximum likelihood method is then used for classifying testing data using the trained models.

Original languageEnglish (US)
Title of host publication1998 IEEE 2nd Workshop on Multimedia Signal Processing
EditorsAbeer Alwan, Antonio Ortega, C.-C. Jay Kuo, C.L. Max Nikias, Ping Wah Wong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages27-32
Number of pages6
ISBN (Electronic)0780349199, 9780780349193
DOIs
StatePublished - 1998
Event2nd IEEE Workshop on Multimedia Signal Processing, MMSP 1998 - Redondo Beach, United States
Duration: Dec 7 1998Dec 9 1998

Publication series

Name1998 IEEE 2nd Workshop on Multimedia Signal Processing
Volume1998-December

Other

Other2nd IEEE Workshop on Multimedia Signal Processing, MMSP 1998
Country/TerritoryUnited States
CityRedondo Beach
Period12/7/9812/9/98

ASJC Scopus subject areas

  • Signal Processing
  • Media Technology

Fingerprint

Dive into the research topics of 'Classification TV programs based on audio information using hidden Markov model'. Together they form a unique fingerprint.

Cite this