Robust audio hashing for audio identification

Hamza Özer, Bülent Sankur, Nasir Memon

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

    Abstract

    We propose and evaluate three new perceptual audio hash functions. These hash functions are based on a concise description of the time-frequency characteristics. This information can be extracted from the time series of frame-by-frame fundamental period or from the singular value decomposition of the mel frequency cepstral parameters. Experiments show that the proposed perceptual hash functions are both robust and unique.

    Original languageEnglish (US)
    Title of host publication2004 12th European Signal Processing Conference, EUSIPCO 2004
    PublisherEuropean Signal Processing Conference, EUSIPCO
    Pages2091-2094
    Number of pages4
    Volume06-10-September-2004
    ISBN (Electronic)9783200001657
    StatePublished - Apr 3 2015
    Event12th European Signal Processing Conference, EUSIPCO 2004 - Vienna, Austria
    Duration: Sep 6 2004Sep 10 2004

    Other

    Other12th European Signal Processing Conference, EUSIPCO 2004
    CountryAustria
    CityVienna
    Period9/6/049/10/04

    Fingerprint

    Hash functions
    Singular value decomposition
    Time series
    Experiments

    ASJC Scopus subject areas

    • Signal Processing
    • Electrical and Electronic Engineering

    Cite this

    Özer, H., Sankur, B., & Memon, N. (2015). Robust audio hashing for audio identification. In 2004 12th European Signal Processing Conference, EUSIPCO 2004 (Vol. 06-10-September-2004, pp. 2091-2094). [7079698] European Signal Processing Conference, EUSIPCO.

    Robust audio hashing for audio identification. / Özer, Hamza; Sankur, Bülent; Memon, Nasir.

    2004 12th European Signal Processing Conference, EUSIPCO 2004. Vol. 06-10-September-2004 European Signal Processing Conference, EUSIPCO, 2015. p. 2091-2094 7079698.

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

    Özer, H, Sankur, B & Memon, N 2015, Robust audio hashing for audio identification. in 2004 12th European Signal Processing Conference, EUSIPCO 2004. vol. 06-10-September-2004, 7079698, European Signal Processing Conference, EUSIPCO, pp. 2091-2094, 12th European Signal Processing Conference, EUSIPCO 2004, Vienna, Austria, 9/6/04.
    Özer H, Sankur B, Memon N. Robust audio hashing for audio identification. In 2004 12th European Signal Processing Conference, EUSIPCO 2004. Vol. 06-10-September-2004. European Signal Processing Conference, EUSIPCO. 2015. p. 2091-2094. 7079698
    Özer, Hamza ; Sankur, Bülent ; Memon, Nasir. / Robust audio hashing for audio identification. 2004 12th European Signal Processing Conference, EUSIPCO 2004. Vol. 06-10-September-2004 European Signal Processing Conference, EUSIPCO, 2015. pp. 2091-2094
    @inproceedings{ae9beb5d8a2342ce98d255a61b9069ab,
    title = "Robust audio hashing for audio identification",
    abstract = "We propose and evaluate three new perceptual audio hash functions. These hash functions are based on a concise description of the time-frequency characteristics. This information can be extracted from the time series of frame-by-frame fundamental period or from the singular value decomposition of the mel frequency cepstral parameters. Experiments show that the proposed perceptual hash functions are both robust and unique.",
    author = "Hamza {\"O}zer and B{\"u}lent Sankur and Nasir Memon",
    year = "2015",
    month = "4",
    day = "3",
    language = "English (US)",
    volume = "06-10-September-2004",
    pages = "2091--2094",
    booktitle = "2004 12th European Signal Processing Conference, EUSIPCO 2004",
    publisher = "European Signal Processing Conference, EUSIPCO",

    }

    TY - GEN

    T1 - Robust audio hashing for audio identification

    AU - Özer, Hamza

    AU - Sankur, Bülent

    AU - Memon, Nasir

    PY - 2015/4/3

    Y1 - 2015/4/3

    N2 - We propose and evaluate three new perceptual audio hash functions. These hash functions are based on a concise description of the time-frequency characteristics. This information can be extracted from the time series of frame-by-frame fundamental period or from the singular value decomposition of the mel frequency cepstral parameters. Experiments show that the proposed perceptual hash functions are both robust and unique.

    AB - We propose and evaluate three new perceptual audio hash functions. These hash functions are based on a concise description of the time-frequency characteristics. This information can be extracted from the time series of frame-by-frame fundamental period or from the singular value decomposition of the mel frequency cepstral parameters. Experiments show that the proposed perceptual hash functions are both robust and unique.

    UR - http://www.scopus.com/inward/record.url?scp=84979917742&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84979917742&partnerID=8YFLogxK

    M3 - Conference contribution

    VL - 06-10-September-2004

    SP - 2091

    EP - 2094

    BT - 2004 12th European Signal Processing Conference, EUSIPCO 2004

    PB - European Signal Processing Conference, EUSIPCO

    ER -