Automatic Musical Instrument and Note Recognition

Sofia Carmen Faria Maia Cavaco

Automatic Musical Instrument and Note Recognition

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We propose a sound recognizer that uses a reduced featureset to identify musical instruments from single notes in sound recordingsas well as the note that was played. The recognizer learns a set of spectralfeatures from the data using non-negative matrix factorization.The accuracy of the recognizer is very high for both instrument and noteclassi cation: the recognition rate for instruments ranged from 94% to100%, while for note identi cation ranged from 86% to 100%.

Original language	Unknown
Title of host publication	Proceedings of INForum
Pages	550-555
Publication status	Published - 1 Jan 2011
Event	INFORUM - Duration: 1 Jan 2011 → …

Conference

Conference	INFORUM
Period	1/01/11 → …

Cite this

@inproceedings{e76f981096604d329b9fb31db0dbac0f,

title = "Automatic Musical Instrument and Note Recognition",

abstract = "We propose a sound recognizer that uses a reduced featureset to identify musical instruments from single notes in sound recordingsas well as the note that was played. The recognizer learns a set of spectralfeatures from the data using non-negative matrix factorization.The accuracy of the recognizer is very high for both instrument and noteclassi cation: the recognition rate for instruments ranged from 94\% to100\%, while for note identi cation ranged from 86\% to 100\%.",

author = "Cavaco, \{Sofia Carmen Faria Maia\}",

year = "2011",

month = jan,

day = "1",

language = "Unknown",

pages = "550--555",

booktitle = "Proceedings of INForum",

note = "INFORUM ; Conference date: 01-01-2011",

}

TY - GEN

T1 - Automatic Musical Instrument and Note Recognition

AU - Cavaco, Sofia Carmen Faria Maia

PY - 2011/1/1

Y1 - 2011/1/1

N2 - We propose a sound recognizer that uses a reduced featureset to identify musical instruments from single notes in sound recordingsas well as the note that was played. The recognizer learns a set of spectralfeatures from the data using non-negative matrix factorization.The accuracy of the recognizer is very high for both instrument and noteclassi cation: the recognition rate for instruments ranged from 94% to100%, while for note identi cation ranged from 86% to 100%.

AB - We propose a sound recognizer that uses a reduced featureset to identify musical instruments from single notes in sound recordingsas well as the note that was played. The recognizer learns a set of spectralfeatures from the data using non-negative matrix factorization.The accuracy of the recognizer is very high for both instrument and noteclassi cation: the recognition rate for instruments ranged from 94% to100%, while for note identi cation ranged from 86% to 100%.

M3 - Conference contribution

SP - 550

EP - 555

BT - Proceedings of INForum

T2 - INFORUM

Y2 - 1 January 2011

ER -