Journal of Northeastern University Natural Science ›› 2018, Vol. 39 ›› Issue (2): 172-175.DOI: 10.12068/j.issn.1005-3026.2018.02.005

• Information & Control • Previous Articles     Next Articles

Audio Commercials Statistics Method Based on Overlapping Cellular Shift

LIU Ji-hong, XIE Li-yan   

  1. School of Information Science & Engineering, Northeastern University, Shenyang 110819, China.
  • Received:2016-08-16 Revised:2016-08-16 Online:2018-02-15 Published:2018-02-09
  • Contact: XIE Li-yan
  • About author:-
  • Supported by:
    -

Abstract: To meet the demand of commercials-monitoring needed by the radio stations, an algorithm of audio commercials detection is proposed based on the overlapping cellular shift (OCS). Different types of commercials are used as research objects in the algorithm because of the diversity of commercials. Based on cellular automaton theory and the characteristics of audio, audio commercials are detected by using the method of the OCS combined the cross-correlation function. The experiment results show that the OCS-based algorithm can quickly and accurately detect the time section when commercials arise, and count the frequency of the commercials broadcasting from the radio, and the algorithm proposed is robust.

Key words: commercial detection, commercial statistics, cross-correlation function, cellular automaton, overlapping cellular shift

CLC Number: