Residual LSTM neural network for time dependent consecutive pitch string recognition from spectrograms: a study on Turkish classical music makams

dc.authoridMIRZA, FUAT KAAN/0000-0002-7664-0632
dc.authoridBaykas, Tuncer/0000-0001-9535-2102
dc.authoridPEKCAN, Onder/0000-0002-0082-8209
dc.authorscopusid58641292900
dc.authorscopusid58642203200
dc.authorscopusid24328990900
dc.authorscopusid57193505462
dc.authorscopusid35479982700
dc.authorwosidMIRZA, FUAT KAAN/JJC-1595-2023
dc.authorwosidPEKCAN, Onder/Y-3158-2018
dc.contributor.authorBaykaş, Tunçer
dc.contributor.authorHekimoğlu, Mustafa
dc.contributor.authorPekcan, Mehmet Önder
dc.contributor.authorHekimoglu, Mustafa
dc.contributor.authorPekcan, Onder
dc.date.accessioned2024-06-23T21:38:25Z
dc.date.available2024-06-23T21:38:25Z
dc.date.issued2023
dc.departmentKadir Has Universityen_US
dc.department-temp[Mirza, Fuat Kaan; Gursoy, Ahmet Fazil; Baykas, Tuncer; Hekimoglu, Mustafa; Pekcan, Onder] Kadir Has Univ, Fac Engn & Nat Sci, Istanbul, Turkiyeen_US
dc.descriptionMIRZA, FUAT KAAN/0000-0002-7664-0632; Baykas, Tuncer/0000-0001-9535-2102; PEKCAN, Onder/0000-0002-0082-8209en_US
dc.description.abstractTurkish classical music, characterized by 'makam', specific melodic configurations delineated by sequential pitches and intervals, is rich in cultural significance and poses a considerable challenge in identifying a musical piece's particular makam. This identification complexity remains an issue even for experienced musical experts, emphasizing the need for automated and accurate classification techniques. In response, we introduce a residual LSTM neural network model that classifies makams by leveraging the distinct sequential pitch patterns discerned within various audio segments over spectrogram-based inputs. This model's design uniquely merges the spatial capabilities of two-dimensional convolutional layers with the temporal understanding of one-dimensional convolutional and LSTM mechanisms embedded within a residual framework. Such an integrated approach allows for detailed temporal analysis of shifting frequencies, as revealed in logarithmically scaled spectrograms, and is adept at recognizing consecutive pitch patterns within segments. Employing stratified cross-validation on a comprehensive dataset encompassing 1154 pieces spanning 15 unique makams, we found that our model demonstrated an accuracy of 95.60% for a subset of 9 makams and 89.09% for all 15 makams. Our approach demonstrated consistent precision even when distinguishing makam pairs known for their closely related pitch sequences. To further validate our model's prowess, we conducted benchmark tests against established methodologies found in current literature, providing a comparative assessment of our proposed workflow's abilities.en_US
dc.identifier.citation0
dc.identifier.doi10.1007/s11042-023-17105-y
dc.identifier.issn1380-7501
dc.identifier.issn1573-7721
dc.identifier.scopus2-s2.0-85173860706
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1007/s11042-023-17105-y
dc.identifier.urihttps://hdl.handle.net/20.500.12469/5797
dc.identifier.wosWOS:001083978800026
dc.identifier.wosqualityN/A
dc.language.isoenen_US
dc.publisherSpringeren_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectMusical information retrievalen_US
dc.subjectPitch sequence recognitionen_US
dc.subjectModal musicen_US
dc.subjectSpectrogramen_US
dc.subjectResidual LSTM neural networken_US
dc.titleResidual LSTM neural network for time dependent consecutive pitch string recognition from spectrograms: a study on Turkish classical music makamsen_US
dc.typeArticleen_US
dspace.entity.typePublication
relation.isAuthorOfPublicationab26f923-9923-42a2-b21e-2dd862cd92be
relation.isAuthorOfPublication533132ce-5631-4068-91c5-2806df0f65bb
relation.isAuthorOfPublicatione5459272-ce6e-44cf-a186-293850946f24
relation.isAuthorOfPublication.latestForDiscoveryab26f923-9923-42a2-b21e-2dd862cd92be

Files