Please use this identifier to cite or link to this item:
https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4910Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Akarawita, S. U. | - |
| dc.date.accessioned | 2025-08-18T06:06:56Z | - |
| dc.date.available | 2025-08-18T06:06:56Z | - |
| dc.date.issued | 2025-06-16 | - |
| dc.identifier.uri | https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4910 | - |
| dc.description.abstract | Abstract 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.iso | en | en_US |
| dc.title | Audio Source Separation and Automatic Music Transcription on Specific Instruments | en_US |
| dc.type | Thesis | en_US |
| Appears in Collections: | 2025 | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 20000073 - S. U. Akarawita - Mr. AKARAWITA S.U.. Copy pdf.pdf | 4.69 MB | Adobe PDF | View/Open |
Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.