Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/7148
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Güven, Erhan | - |
dc.contributor.author | Özbayoğlu, Ahmet Murat | - |
dc.date.accessioned | 2021-09-11T15:55:48Z | - |
dc.date.available | 2021-09-11T15:55:48Z | - |
dc.date.issued | 2012 | en_US |
dc.identifier.citation | Conference on Complex Adaptive Systems -- NOV 14-16, 2012 -- Washington, DC | en_US |
dc.identifier.issn | 1877-0509 | - |
dc.identifier.uri | https://doi.org/10.1016/j.procs.2012.09.051 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.11851/7148 | - |
dc.description.abstract | In recent years, very large scale online music databases containing more than 10 million tracks became prevalent as the fostered availability of streaming and downloading services via the World-Wide Web. The set of access schemes, or Music Information Retrieval (MIR), still poses several and partially solved problems, especially the personalization of the access, such as query by humming, melody, mood, style, genre, instrument, etc. Generally the previous approaches utilized the spectral features of the music track and extracted several high-level features such as pitch, cepstral coefficients, power, and the time-domain features such as onset, tempo, etc. In this work, however, the low-level local features of the spectrogram partitioned by means of the Bark scale are utilized to extract the quantized time-frequency-power features to be used by a Support Vector Machine to classify the notes (melody) and the timbre (instrument) of 128 instruments of General Midi standard. A database of 3-second sound clips of notes C4 to C5 on 7 sound cards using two software synthesizers is constructed and used for experimental note and timbre classification. The preliminary results of 13-category music note and 16-category timbre classifications are promising and their performance scores are surpassing the previously proposed methods. | en_US |
dc.description.sponsorship | Missouri Univ Sci & Technol, Lockheed Martin, Mocana, Tata Consultancy Serv, GAK3, Drexel Univ Online, Hark.com | en_US |
dc.language.iso | en | en_US |
dc.publisher | Elsevier Science Bv | en_US |
dc.relation.ispartof | Complex Adaptive Systems 2012 | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | Music information retrieval | en_US |
dc.subject | music note | en_US |
dc.subject | timbre | en_US |
dc.subject | spectrogram features | en_US |
dc.subject | statistical learning | en_US |
dc.title | Note and Timbre Classification by Local Features of Spectrogram | en_US |
dc.type | Conference Object | en_US |
dc.relation.ispartofseries | Procedia Computer Science | en_US |
dc.department | Faculties, Faculty of Engineering, Department of Computer Engineering | en_US |
dc.department | Fakülteler, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü | tr_TR |
dc.identifier.volume | 12 | en_US |
dc.identifier.startpage | 182 | en_US |
dc.identifier.endpage | 187 | en_US |
dc.authorid | 0000-0001-7998-5735 | - |
dc.identifier.wos | WOS:000314992600027 | en_US |
dc.identifier.scopus | 2-s2.0-84897005307 | en_US |
dc.institutionauthor | Özbayoğlu, Ahmet Murat | - |
dc.identifier.doi | 10.1016/j.procs.2012.09.051 | - |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | en_US |
dc.relation.conference | Conference on Complex Adaptive Systems | en_US |
dc.identifier.scopusquality | - | - |
item.openairetype | Conference Object | - |
item.languageiso639-1 | en | - |
item.grantfulltext | none | - |
item.fulltext | No Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.cerifentitytype | Publications | - |
crisitem.author.dept | 02.1. Department of Artificial Intelligence Engineering | - |
Appears in Collections: | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
CORE Recommender
SCOPUSTM
Citations
1
checked on Dec 21, 2024
WEB OF SCIENCETM
Citations
4
checked on Oct 5, 2024
Page view(s)
66
checked on Dec 16, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.