An automatic singing impression estimation method using factor analysis and multiple regression

Ai Kanato, Tomoyasu Nakano, Masataka Goto, Hideaki Kikuchi

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

    2 Citations (Scopus)

    Abstract

    This paper describes a method for estimating the impression of a singing voice via acoustic features. While much research has been conducted on singing impression, to date no method for determining appropriate words to represent the impressions created by a person's singing has been developed, primarily due to the lack of a comprehensive evaluation scale. We followed two steps: construction of such an impression scale, and development of models for estimating the impression score of each word. In the scale construction, two experiments were carried out. Firstly, 44 words were selected as relevant words based on subjective evaluation. Secondly, 12 words were selected as an impression scale, and three factors ("powerful", "cautious", and "cheerful") were extracted by factor analysis. To estimate impression scores, multiple regression models were constructed for each impression word with acoustic features. The models were tested by cross validation. The average R2 value for the 12 words of the complete scale was 0.567, and the R2 for the three factors were 0.863 (powerful), 0.381 (cautious), and 0.603 (cheerful).

    Original languageEnglish
    Title of host publicationProceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos
    PublisherNational and Kapodistrian University of Athens
    Pages1244-1251
    Number of pages8
    ISBN (Print)9789604661374
    Publication statusPublished - 2014
    Event40th International Computer Music Conference, ICMC 2014, Joint with the 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos - Athens
    Duration: 2014 Sep 142014 Sep 20

    Other

    Other40th International Computer Music Conference, ICMC 2014, Joint with the 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos
    CityAthens
    Period14/9/1414/9/20

    Fingerprint

    Factor analysis
    Acoustics
    Multiple Regression
    Factor Analysis
    Experiments

    ASJC Scopus subject areas

    • Music
    • Media Technology
    • Computer Science Applications

    Cite this

    Kanato, A., Nakano, T., Goto, M., & Kikuchi, H. (2014). An automatic singing impression estimation method using factor analysis and multiple regression. In Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos (pp. 1244-1251). National and Kapodistrian University of Athens.

    An automatic singing impression estimation method using factor analysis and multiple regression. / Kanato, Ai; Nakano, Tomoyasu; Goto, Masataka; Kikuchi, Hideaki.

    Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos. National and Kapodistrian University of Athens, 2014. p. 1244-1251.

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

    Kanato, A, Nakano, T, Goto, M & Kikuchi, H 2014, An automatic singing impression estimation method using factor analysis and multiple regression. in Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos. National and Kapodistrian University of Athens, pp. 1244-1251, 40th International Computer Music Conference, ICMC 2014, Joint with the 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos, Athens, 14/9/14.
    Kanato A, Nakano T, Goto M, Kikuchi H. An automatic singing impression estimation method using factor analysis and multiple regression. In Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos. National and Kapodistrian University of Athens. 2014. p. 1244-1251
    Kanato, Ai ; Nakano, Tomoyasu ; Goto, Masataka ; Kikuchi, Hideaki. / An automatic singing impression estimation method using factor analysis and multiple regression. Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos. National and Kapodistrian University of Athens, 2014. pp. 1244-1251
    @inproceedings{eefdf00707294c34bc78ed7fd8192346,
    title = "An automatic singing impression estimation method using factor analysis and multiple regression",
    abstract = "This paper describes a method for estimating the impression of a singing voice via acoustic features. While much research has been conducted on singing impression, to date no method for determining appropriate words to represent the impressions created by a person's singing has been developed, primarily due to the lack of a comprehensive evaluation scale. We followed two steps: construction of such an impression scale, and development of models for estimating the impression score of each word. In the scale construction, two experiments were carried out. Firstly, 44 words were selected as relevant words based on subjective evaluation. Secondly, 12 words were selected as an impression scale, and three factors ({"}powerful{"}, {"}cautious{"}, and {"}cheerful{"}) were extracted by factor analysis. To estimate impression scores, multiple regression models were constructed for each impression word with acoustic features. The models were tested by cross validation. The average R2 value for the 12 words of the complete scale was 0.567, and the R2 for the three factors were 0.863 (powerful), 0.381 (cautious), and 0.603 (cheerful).",
    author = "Ai Kanato and Tomoyasu Nakano and Masataka Goto and Hideaki Kikuchi",
    year = "2014",
    language = "English",
    isbn = "9789604661374",
    pages = "1244--1251",
    booktitle = "Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos",
    publisher = "National and Kapodistrian University of Athens",

    }

    TY - GEN

    T1 - An automatic singing impression estimation method using factor analysis and multiple regression

    AU - Kanato, Ai

    AU - Nakano, Tomoyasu

    AU - Goto, Masataka

    AU - Kikuchi, Hideaki

    PY - 2014

    Y1 - 2014

    N2 - This paper describes a method for estimating the impression of a singing voice via acoustic features. While much research has been conducted on singing impression, to date no method for determining appropriate words to represent the impressions created by a person's singing has been developed, primarily due to the lack of a comprehensive evaluation scale. We followed two steps: construction of such an impression scale, and development of models for estimating the impression score of each word. In the scale construction, two experiments were carried out. Firstly, 44 words were selected as relevant words based on subjective evaluation. Secondly, 12 words were selected as an impression scale, and three factors ("powerful", "cautious", and "cheerful") were extracted by factor analysis. To estimate impression scores, multiple regression models were constructed for each impression word with acoustic features. The models were tested by cross validation. The average R2 value for the 12 words of the complete scale was 0.567, and the R2 for the three factors were 0.863 (powerful), 0.381 (cautious), and 0.603 (cheerful).

    AB - This paper describes a method for estimating the impression of a singing voice via acoustic features. While much research has been conducted on singing impression, to date no method for determining appropriate words to represent the impressions created by a person's singing has been developed, primarily due to the lack of a comprehensive evaluation scale. We followed two steps: construction of such an impression scale, and development of models for estimating the impression score of each word. In the scale construction, two experiments were carried out. Firstly, 44 words were selected as relevant words based on subjective evaluation. Secondly, 12 words were selected as an impression scale, and three factors ("powerful", "cautious", and "cheerful") were extracted by factor analysis. To estimate impression scores, multiple regression models were constructed for each impression word with acoustic features. The models were tested by cross validation. The average R2 value for the 12 words of the complete scale was 0.567, and the R2 for the three factors were 0.863 (powerful), 0.381 (cautious), and 0.603 (cheerful).

    UR - http://www.scopus.com/inward/record.url?scp=84908873176&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84908873176&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 9789604661374

    SP - 1244

    EP - 1251

    BT - Proceedings - 40th International Computer Music Conference, ICMC 2014 and 11th Sound and Music Computing Conference, SMC 2014 - Music Technology Meets Philosophy: From Digital Echos to Virtual Ethos

    PB - National and Kapodistrian University of Athens

    ER -