Please use this identifier to cite or link to this item: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4910
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAkarawita, S. U.-
dc.date.accessioned2025-08-18T06:06:56Z-
dc.date.available2025-08-18T06:06:56Z-
dc.date.issued2025-06-16-
dc.identifier.urihttps://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4910-
dc.description.abstractAbstract Imagine listeningtoasymphonywhereviolins,pianos,anddrumsblendseamlessly, creating arichmusicalexperience.Butwhatifwecouldisolatejusttheviolinfromthat mix, capturingitsmelodieswithprecision?Thisistheessenceofaudiosourceseparation, whichisknownasextractingindividualinstrumentsfromacomplexmusicalpiece. Atthesametime,musictranscriptionhaslongbeenataskrequiringhumanexpertise. Turninganaudiorecordingintomusicalnotes(MIDI)hastraditionallybeenamanual process,demandingatrainedear.However,withadvancesinmachinelearning,wenow havethepotentialtoautomatethisprocess,makingmusicmoreaccessible,editable,and analyzable. This researchfocusesondevelopingmachinelearningmodelsthatcanseparatecertain instrumentalaudiofrompolyphonicrecordingsandconvertitintoMIDI.Bybridgingthe fields ofaudiosourceseparationandautomaticmusictranscription(AMT),weaimto push theboundariesofhowmachinesunderstandandprocessmusic.en_US
dc.language.isoenen_US
dc.titleAudio Source Separation and Automatic Music Transcription on Specific Instrumentsen_US
dc.typeThesisen_US
Appears in Collections:2025

Files in This Item:
File Description SizeFormat 
20000073 - S. U. Akarawita - Mr. AKARAWITA S.U.. Copy pdf.pdf4.69 MBAdobe PDFView/Open


Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.