Disentangling overlapping sources: improving vocal and violin source separation in Carnatic Music

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Shankar, Adithi
• dc.contributor.author Schweinitz, Serafin
• dc.contributor.author Plaja-Roglans, Genís
• dc.contributor.author Serra, Xavier
• dc.contributor.author Rocamora, Rodrigo
• dc.date.accessioned 2025-06-05T13:01:32Z
• dc.date.embargoEnd info:eu-repo/date/embargoEnd/2027-27-05
• dc.date.issued 2025
• dc.description.abstract Separating the individual elements in a music mixture is an important tool in computational musicology, allowing for an improved analysis of music repertoires. In the context of Carnatic music, this task remains a challenge given the suboptimal generalization of existing music source separation systems to this style. Although multi-stem Carnatic recordings exist, these are mostly collected from the mixing console in live performances. Therefore, there is an unintended presence of other sources in the background of the audio signal of an individual instrument. Another challenge for Carnatic music is the strong melodic correlation between the singing voice and the violin, two sources widely found in live performances of this repertoire. Existing strategies to address such problems struggle with source quality and only consider vocals. In this work, we propose to incorporate two components in the regular training scheme of a source separation network, namely a learned loss and a mixer model, to account for the source bleeding. We achieve improved separation while extending the separation targets to the violin, an important source in the repertoire, and therefore cover the separation of the most common melodic components in Carnatic Music. Code and models are available in compiam.
• dc.description.sponsorship This work was supported by PID2020-112584RB-C33, PID2023-146692OB-C33, CEX2021-001195-M funded by MICIU/AEI/10.13039/501100011033, UPF-PlaCLIK and SGR 00930. DHL (Serra Húnter) also acknowledges the support by ICREA Academia.
• dc.embargo.liftdate 2029-03-05
• dc.format.mimetype application/pdf
• dc.identifier.citation Shankar A, Schweinitz S, Plaja-Roglans G, Serra X, Rocamora M. Disentangling overlapping sources: improving vocal and violin source separation in Carnatic music. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2025 April 6-11; Hyderabad, India.
• dc.identifier.uri http://hdl.handle.net/10230/70626
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.ispartof IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2025 April 6-11; Hyderabad, India.
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PID2020-112584RB-C33
• dc.relation.projectID info:eu-repo/grantAgreement/ES/3PE/PID2023-146692OB-C33
• dc.rights © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/ICASSPW65056.2025.11011027
• dc.rights.accessRights info:eu-repo/semantics/embargoedAccess
• dc.subject.keyword Music source separation
• dc.subject.keyword Carnatic music
• dc.subject.keyword Source Bleeding
• dc.subject.keyword Violin separation
• dc.title Disentangling overlapping sources: improving vocal and violin source separation in Carnatic Music
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion