• DocumentCode
    714369
  • Title

    Impulsive sound detection and gunshot recognition

  • Author

    Arslan, Yuksel ; Guldogan, Burak

  • Author_Institution
    Elektrik ve Elektron. Muhendisligi Bolumu, Turgut Ozal Univ., Ankara, Turkey
  • fYear
    2015
  • fDate
    16-19 May 2015
  • Firstpage
    511
  • Lastpage
    514
  • Abstract
    Detection of impulsive sounds may be required for different kind of purposes. The first step of sniper detection systems requires the detection of impulsive sounds. Gunshot detection and recognition systems must detect at first impulsive sounds too. For security systems, the detection of impulsive sounds such as glass or door breaking, screaming can be important. Deaf persons can be warned of car horns, alarms and sirens by way of impulsive sound detection systems. The main aim of this paper is the detection and recognition of the impulsive sounds caused by gunshots. Thus gunshot acoustic is investigated for this purpose. The developed methods have higher detection and low false alarm rates than the other impulsive sound detection systems. The proposed gunshot recognition algorithm recognizes the gunshot among the same kind of sounds with very high probability.
  • Keywords
    acoustic signal processing; impulse noise; probability; support vector machines; weapons; alarms; car horns; deaf persons; door breaking sound; false alarm rates; glass breaking sound; gunshot acoustic; gunshot detection systems; gunshot recognition system; impulsive sound detection; probability; screaming sound; security systems; sirens; sniper detection systems; support vector machine; Conferences; Hidden Markov models; Mel frequency cepstral coefficient; Noise measurement; Signal to noise ratio; Support Vector Machine (SVM); gunshot acoustic; gunshot detectio; gunshot recognition; impulsive sound;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing and Communications Applications Conference (SIU), 2015 23th
  • Conference_Location
    Malatya
  • Type

    conf

  • DOI
    10.1109/SIU.2015.7129872
  • Filename
    7129872