Unified inter- and intra-recording duration model for multiple music audio alignment

Akira Maezawa, Katsutoshi Itoyama, Kazuyoshi Yoshii, Hiroshi G. Okuno

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

    2 Citations (Scopus)

    Abstract

    This paper presents a probabilistic audio-to-audio alignment method that focuses on the relationship among the note durations of different performances of a piece of music. A key issue in probabilistic audio alignment methods is in expressing how interrelated are the durations of notes in the underlying piece of music. Existing studies focus either on the duration of adjacent notes within a recording (intra-recording duration model), or the duration of a given note across different recordings (inter-recording duration model). This paper unifies these approaches through a simple modification to them. Furthermore, the paper extends the unified model, allowing the dynamics of the note duration to change sporadically. Experimental evaluation demonstrated that the proposed models decrease the alignment error.

    Original languageEnglish
    Title of host publication2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Print)9781479974504
    DOIs
    Publication statusPublished - 2015 Nov 24
    EventIEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015 - New Paltz, United States
    Duration: 2015 Oct 182015 Oct 21

    Other

    OtherIEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015
    CountryUnited States
    CityNew Paltz
    Period15/10/1815/10/21

    Keywords

    • audio alignment
    • hierarchical Bayesian model
    • music information retrieval

    ASJC Scopus subject areas

    • Computer Science Applications
    • Signal Processing
    • Media Technology

    Cite this

    Maezawa, A., Itoyama, K., Yoshii, K., & Okuno, H. G. (2015). Unified inter- and intra-recording duration model for multiple music audio alignment. In 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015 [7336929] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WASPAA.2015.7336929

    Unified inter- and intra-recording duration model for multiple music audio alignment. / Maezawa, Akira; Itoyama, Katsutoshi; Yoshii, Kazuyoshi; Okuno, Hiroshi G.

    2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7336929.

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

    Maezawa, A, Itoyama, K, Yoshii, K & Okuno, HG 2015, Unified inter- and intra-recording duration model for multiple music audio alignment. in 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015., 7336929, Institute of Electrical and Electronics Engineers Inc., IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015, New Paltz, United States, 15/10/18. https://doi.org/10.1109/WASPAA.2015.7336929
    Maezawa A, Itoyama K, Yoshii K, Okuno HG. Unified inter- and intra-recording duration model for multiple music audio alignment. In 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7336929 https://doi.org/10.1109/WASPAA.2015.7336929
    Maezawa, Akira ; Itoyama, Katsutoshi ; Yoshii, Kazuyoshi ; Okuno, Hiroshi G. / Unified inter- and intra-recording duration model for multiple music audio alignment. 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015. Institute of Electrical and Electronics Engineers Inc., 2015.
    @inproceedings{6d8dc15cae6d48ce860f3978133808bb,
    title = "Unified inter- and intra-recording duration model for multiple music audio alignment",
    abstract = "This paper presents a probabilistic audio-to-audio alignment method that focuses on the relationship among the note durations of different performances of a piece of music. A key issue in probabilistic audio alignment methods is in expressing how interrelated are the durations of notes in the underlying piece of music. Existing studies focus either on the duration of adjacent notes within a recording (intra-recording duration model), or the duration of a given note across different recordings (inter-recording duration model). This paper unifies these approaches through a simple modification to them. Furthermore, the paper extends the unified model, allowing the dynamics of the note duration to change sporadically. Experimental evaluation demonstrated that the proposed models decrease the alignment error.",
    keywords = "audio alignment, hierarchical Bayesian model, music information retrieval",
    author = "Akira Maezawa and Katsutoshi Itoyama and Kazuyoshi Yoshii and Okuno, {Hiroshi G.}",
    year = "2015",
    month = "11",
    day = "24",
    doi = "10.1109/WASPAA.2015.7336929",
    language = "English",
    isbn = "9781479974504",
    booktitle = "2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Unified inter- and intra-recording duration model for multiple music audio alignment

    AU - Maezawa, Akira

    AU - Itoyama, Katsutoshi

    AU - Yoshii, Kazuyoshi

    AU - Okuno, Hiroshi G.

    PY - 2015/11/24

    Y1 - 2015/11/24

    N2 - This paper presents a probabilistic audio-to-audio alignment method that focuses on the relationship among the note durations of different performances of a piece of music. A key issue in probabilistic audio alignment methods is in expressing how interrelated are the durations of notes in the underlying piece of music. Existing studies focus either on the duration of adjacent notes within a recording (intra-recording duration model), or the duration of a given note across different recordings (inter-recording duration model). This paper unifies these approaches through a simple modification to them. Furthermore, the paper extends the unified model, allowing the dynamics of the note duration to change sporadically. Experimental evaluation demonstrated that the proposed models decrease the alignment error.

    AB - This paper presents a probabilistic audio-to-audio alignment method that focuses on the relationship among the note durations of different performances of a piece of music. A key issue in probabilistic audio alignment methods is in expressing how interrelated are the durations of notes in the underlying piece of music. Existing studies focus either on the duration of adjacent notes within a recording (intra-recording duration model), or the duration of a given note across different recordings (inter-recording duration model). This paper unifies these approaches through a simple modification to them. Furthermore, the paper extends the unified model, allowing the dynamics of the note duration to change sporadically. Experimental evaluation demonstrated that the proposed models decrease the alignment error.

    KW - audio alignment

    KW - hierarchical Bayesian model

    KW - music information retrieval

    UR - http://www.scopus.com/inward/record.url?scp=84960925605&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84960925605&partnerID=8YFLogxK

    U2 - 10.1109/WASPAA.2015.7336929

    DO - 10.1109/WASPAA.2015.7336929

    M3 - Conference contribution

    SN - 9781479974504

    BT - 2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, WASPAA 2015

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -