Efficient automated piano - Guitar timbre classification

Exarhos, M; Papaodysseus, C; Fragoulis, D; Panagopoulos, Th; Alexiou, C; Roussopoulos, G

dc.contributor.author	Exarhos, M	en
dc.contributor.author	Papaodysseus, C	en
dc.contributor.author	Fragoulis, D	en
dc.contributor.author	Panagopoulos, Th	en
dc.contributor.author	Alexiou, C	en
dc.contributor.author	Roussopoulos, G	en
dc.date.accessioned	2014-03-01T01:51:52Z
dc.date.available	2014-03-01T01:51:52Z
dc.date.issued	2002	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/26485
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-4944229172&partnerID=40&md5=efb9efde163473ccf52819ed96106456	en
dc.subject	Automated timbre classification	en
dc.subject	Instrument identification	en
dc.subject	Timbre perception	en
dc.subject	Timbre recognition	en
dc.subject.other	Data acquisition	en
dc.subject.other	Frequency domain analysis	en
dc.subject.other	Neural networks	en
dc.subject.other	Pattern recognition	en
dc.subject.other	Statistical methods	en
dc.subject.other	Timber	en
dc.subject.other	Automated timbre classification	en
dc.subject.other	Instrument identification	en
dc.subject.other	Timbre perception	en
dc.subject.other	Timbre recognition	en
dc.subject.other	Musical instruments	en
dc.subject.other	Data Processing	en
dc.subject.other	Lumber	en
dc.subject.other	Neural Networks	en
dc.subject.other	Pattern Recognition	en
dc.subject.other	Statistical Methods	en
dc.title	Efficient automated piano - Guitar timbre classification	en
heal.type	journalArticle	en
heal.publicationDate	2002	en
heal.abstract	In this paper it is pointed out that there is a new decisively important factor in both the perceptual as well as the automated instrument identification process. This factor is determined by the inharmonic spectral content of a note, while it is, in practice, totally independent of the note spectrum harmonic part. This conclusion is based on a number of extended acoustical experiments, performed on six hundred twelve (612) isolated guitar notes and nine hundred twenty six (926) isolated piano notes, over the full pitch range of each instrument. The notes have been recorded from six different performers where each one played a different instrument. Next, a number of powerful criteria for the classification between guitar and piano are proposed. Using these criteria, automated classification between 754 piano and guitar test notes has been achieved with a hundred percent (100%) success rate.	en
heal.publisher	World Scientific and Engineering Academy and Society	en
heal.journalName	Recent Advances in Computers, Computing and Communications	en
dc.identifier.spage	235	en
dc.identifier.epage	240	en