[Zurück]


Vorträge und Posterpräsentationen (mit Tagungsband-Eintrag):

R. Neumayer, A. Rauber:
"Integration of text and audio features for genre classification in music information retrieval";
Poster: ECIR 2007, Rom, Italien; 02.04.2007 - 05.04.2007; in: "Advances in Information Retrieval", Springer, Lecture Notes in Computer Science/Volume 4425 2007 (2007), ISBN: 978-3-540-71494-1; S. 724 - 727.



Kurzfassung deutsch:
Abstract. Multimedia content can be described in versatile ways as
its essence is not limited to one view. For music data these multiple views could be a song´s audio features as well as its lyrics. Both of these modalities have their advantages as text may be easier to search in and could cover more of the `content semantics´ of a song, while omitting other types of semantic categorisation. (Psycho)acoustic feature sets, on the other hand, provide the means to identify tracks that `sound similar´ while less supporting other kinds of semantic categorisation. Those discerning characteristics of different feature sets meet users´ differing information needs. We will explain the nature of text and audio feature sets which describe the same audio tracks. Moreover, we will propose the use of textual data on top of low level audio features for music genre classification. Further, we will show the impact of different combinations of audio features and textual features based on content words.

Kurzfassung englisch:
Abstract. Multimedia content can be described in versatile ways as
its essence is not limited to one view. For music data these multiple views could be a song´s audio features as well as its lyrics. Both of these modalities have their advantages as text may be easier to search in and could cover more of the `content semantics´ of a song, while omitting other types of semantic categorisation. (Psycho)acoustic feature sets, on the other hand, provide the means to identify tracks that `sound similar´ while less supporting other kinds of semantic categorisation. Those discerning characteristics of different feature sets meet users´ differing information needs. We will explain the nature of text and audio feature sets which describe the same audio tracks. Moreover, we will propose the use of textual data on top of low level audio features for music genre classification. Further, we will show the impact of different combinations of audio features and textual features based on content words.

Schlagworte:
music information retrieval, musical genre classification, multi-modal classification, lyrics, text analysis


"Offizielle" elektronische Version der Publikation (entsprechend ihrem Digital Object Identifier - DOI)
http://dx.doi.org/10.1007/978-3-540-71496-5_78

Elektronische Version der Publikation:
http://publik.tuwien.ac.at/files/pub-inf_4727.pdf


Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.