• DocumentCode
    1968461
  • Title

    Audio patterns searching and retrieval

  • Author

    Gubka, Róbert ; Kuba, Michal

  • Author_Institution
    Dept. of Telecommun. & Multimedia, Univ. of Zilina, Žilina, Slovakia
  • fYear
    2011
  • fDate
    19-20 April 2011
  • Firstpage
    1
  • Lastpage
    3
  • Abstract
    Pattern searching and retrieval plays important role in task of content-based audio analysis for requirements of media database management or in surveillance systems for detecting significant audio events and keywords. In the paper, we present algorithm for spotting audio patterns in record, using Hidden Markov Models and Viterbi decoder. Also, two types of probability normalization are presented and compared. Performance of proposed algorithm was evaluated on database of slovak spoken numbers.
  • Keywords
    Viterbi decoding; audio coding; content-based retrieval; hidden Markov models; probability; Viterbi decoder; audio pattern retrieval; audio pattern searching; hidden Markov model; media database management; surveillance system; Computational modeling; Data models; Decoding; Hidden Markov models; Mathematical model; Speech; Training; audio modeling; pattern retrieval; sequence decoding;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Radioelektronika (RADIOELEKTRONIKA), 2011 21st International Conference
  • Conference_Location
    Brno
  • Print_ISBN
    978-1-61284-325-4
  • Type

    conf

  • DOI
    10.1109/RADIOELEK.2011.5936407
  • Filename
    5936407