Latent topic similarity for music retrieval and its application to a system that supports DJ performance

Tatsunori Hirai, Hironori Doi, Shigeo Morishima

    研究成果: Article

    抄録

    This paper presents a topic modeling method to retrieve similar music fragments and its application, Music- Mixer, which is a computer-aided DJ system that supports DJ performance by automatically mixing songs in a seamless manner. MusicMixer mixes songs based on audio similarity calculated via beat analysis and latent topic analysis of the chromatic signal in the audio. The topic represents latent semantics on how chromatic sounds are generated. Given a list of songs, a DJ selects a song with beats and sounds similar to a specific point of the currently playing song to seamlessly transition between songs. By calculating similarities between all existing song sections that can be naturally mixed, MusicMixer retrieves the best mixing point from a myriad of possibilities and enables seamless song transitions. Although it is comparatively easy to calculate beat similarity from audio signals, considering the semantics of songs from the viewpoint of a human DJ has proven difficult. Therefore, we propose a method to represent audio signals to construct topic models that acquire latent semantics of audio. The results of a subjective experiment demonstrate the effectiveness of the proposed latent semantic analysis method. MusicMixer achieves automatic song mixing using the audio signal processing approach; thus, users can perform DJ mixing simply by selecting a song from a list of songs suggested by the system.

    元の言語English
    ページ(範囲)276-284
    ページ数9
    ジャーナルJournal of Information Processing
    26
    DOI
    出版物ステータスPublished - 2018 1 1

    Fingerprint

    Semantics
    Audio signal processing
    Acoustic waves
    Computer music
    Experiments

    ASJC Scopus subject areas

    • Computer Science(all)

    これを引用

    @article{11ebc96c3f504e6986dce130ef2e22c5,
    title = "Latent topic similarity for music retrieval and its application to a system that supports DJ performance",
    abstract = "This paper presents a topic modeling method to retrieve similar music fragments and its application, Music- Mixer, which is a computer-aided DJ system that supports DJ performance by automatically mixing songs in a seamless manner. MusicMixer mixes songs based on audio similarity calculated via beat analysis and latent topic analysis of the chromatic signal in the audio. The topic represents latent semantics on how chromatic sounds are generated. Given a list of songs, a DJ selects a song with beats and sounds similar to a specific point of the currently playing song to seamlessly transition between songs. By calculating similarities between all existing song sections that can be naturally mixed, MusicMixer retrieves the best mixing point from a myriad of possibilities and enables seamless song transitions. Although it is comparatively easy to calculate beat similarity from audio signals, considering the semantics of songs from the viewpoint of a human DJ has proven difficult. Therefore, we propose a method to represent audio signals to construct topic models that acquire latent semantics of audio. The results of a subjective experiment demonstrate the effectiveness of the proposed latent semantic analysis method. MusicMixer achieves automatic song mixing using the audio signal processing approach; thus, users can perform DJ mixing simply by selecting a song from a list of songs suggested by the system.",
    keywords = "Automatic song mixing, Computer-aided performance, Topic analysis",
    author = "Tatsunori Hirai and Hironori Doi and Shigeo Morishima",
    year = "2018",
    month = "1",
    day = "1",
    doi = "10.2197/ipsjjip.26.276",
    language = "English",
    volume = "26",
    pages = "276--284",
    journal = "Journal of Information Processing",
    issn = "0387-5806",
    publisher = "Information Processing Society of Japan",

    }

    TY - JOUR

    T1 - Latent topic similarity for music retrieval and its application to a system that supports DJ performance

    AU - Hirai, Tatsunori

    AU - Doi, Hironori

    AU - Morishima, Shigeo

    PY - 2018/1/1

    Y1 - 2018/1/1

    N2 - This paper presents a topic modeling method to retrieve similar music fragments and its application, Music- Mixer, which is a computer-aided DJ system that supports DJ performance by automatically mixing songs in a seamless manner. MusicMixer mixes songs based on audio similarity calculated via beat analysis and latent topic analysis of the chromatic signal in the audio. The topic represents latent semantics on how chromatic sounds are generated. Given a list of songs, a DJ selects a song with beats and sounds similar to a specific point of the currently playing song to seamlessly transition between songs. By calculating similarities between all existing song sections that can be naturally mixed, MusicMixer retrieves the best mixing point from a myriad of possibilities and enables seamless song transitions. Although it is comparatively easy to calculate beat similarity from audio signals, considering the semantics of songs from the viewpoint of a human DJ has proven difficult. Therefore, we propose a method to represent audio signals to construct topic models that acquire latent semantics of audio. The results of a subjective experiment demonstrate the effectiveness of the proposed latent semantic analysis method. MusicMixer achieves automatic song mixing using the audio signal processing approach; thus, users can perform DJ mixing simply by selecting a song from a list of songs suggested by the system.

    AB - This paper presents a topic modeling method to retrieve similar music fragments and its application, Music- Mixer, which is a computer-aided DJ system that supports DJ performance by automatically mixing songs in a seamless manner. MusicMixer mixes songs based on audio similarity calculated via beat analysis and latent topic analysis of the chromatic signal in the audio. The topic represents latent semantics on how chromatic sounds are generated. Given a list of songs, a DJ selects a song with beats and sounds similar to a specific point of the currently playing song to seamlessly transition between songs. By calculating similarities between all existing song sections that can be naturally mixed, MusicMixer retrieves the best mixing point from a myriad of possibilities and enables seamless song transitions. Although it is comparatively easy to calculate beat similarity from audio signals, considering the semantics of songs from the viewpoint of a human DJ has proven difficult. Therefore, we propose a method to represent audio signals to construct topic models that acquire latent semantics of audio. The results of a subjective experiment demonstrate the effectiveness of the proposed latent semantic analysis method. MusicMixer achieves automatic song mixing using the audio signal processing approach; thus, users can perform DJ mixing simply by selecting a song from a list of songs suggested by the system.

    KW - Automatic song mixing

    KW - Computer-aided performance

    KW - Topic analysis

    UR - http://www.scopus.com/inward/record.url?scp=85043983409&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85043983409&partnerID=8YFLogxK

    U2 - 10.2197/ipsjjip.26.276

    DO - 10.2197/ipsjjip.26.276

    M3 - Article

    VL - 26

    SP - 276

    EP - 284

    JO - Journal of Information Processing

    JF - Journal of Information Processing

    SN - 0387-5806

    ER -