{"id":"https://openalex.org/W7166845435","doi":"https://doi.org/10.1145/3815723.3815730","title":"A R\u0101ga Independent Encoder for Svara Representation in Carnatic Music","display_name":"A R\u0101ga Independent Encoder for Svara Representation in Carnatic Music","publication_year":2026,"publication_date":"2026-07-01","ids":{"openalex":"https://openalex.org/W7166845435","doi":"https://doi.org/10.1145/3815723.3815730"},"language":null,"primary_location":{"id":"doi:10.1145/3815723.3815730","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815723.3815730","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3815723.3815730","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123253531","display_name":"Vivek Vijayan","orcid":null},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Vivek Vijayan","raw_affiliation_strings":["Universitat Pompeu Fabra, Barcelona, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0009-0002-9153-7868","affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra, Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071780141","display_name":"Thomas Nuttall","orcid":"https://orcid.org/0000-0001-6316-1424"},"institutions":[{"id":"https://openalex.org/I2799601783","display_name":"Escola Superior de M\u00fasica de Catalunya","ror":"https://ror.org/053d21744","country_code":"ES","type":"education","lineage":["https://openalex.org/I2799601783"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Thomas Nuttall","raw_affiliation_strings":["Music Technology Group, Barcelona, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6316-1424","affiliations":[{"raw_affiliation_string":"Music Technology Group, Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I2799601783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I2799601783","display_name":"Escola Superior de M\u00fasica de Catalunya","ror":"https://ror.org/053d21744","country_code":"ES","type":"education","lineage":["https://openalex.org/I2799601783"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Music Technology Group, Barcelona, Barcelona, Spain"],"raw_orcid":"https://orcid.org/0000-0003-1395-2345","affiliations":[{"raw_affiliation_string":"Music Technology Group, Barcelona, Barcelona, Spain","institution_ids":["https://openalex.org/I2799601783"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86309715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"56","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5472999811172485,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5472999811172485,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.24899999797344208,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.0877000018954277,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.758899986743927},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7016000151634216},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.46650001406669617},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4262000024318695},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.32440000772476196},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3237000107765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803000211715698},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.758899986743927},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7016000151634216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578000009059906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5727999806404114},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5663999915122986},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.46650001406669617},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2648000121116638}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3815723.3815730","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815723.3815730","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3815723.3815730","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3815723.3815730","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6548449993133545,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2007295997","https://openalex.org/W2058715312","https://openalex.org/W2133254377","https://openalex.org/W2138621090","https://openalex.org/W2169081556","https://openalex.org/W2334665416","https://openalex.org/W2342396520","https://openalex.org/W2601243251","https://openalex.org/W2972810968","https://openalex.org/W2993167074","https://openalex.org/W3046296398","https://openalex.org/W3145093226","https://openalex.org/W4319350696","https://openalex.org/W4399876248","https://openalex.org/W4403913082","https://openalex.org/W7103883615"],"related_works":[],"abstract_inverted_index":{"Learning":[0],"effective":[1],"representations":[2],"for":[3],"svaras":[4],"(notes)":[5],"in":[6,63],"Carnatic":[7,40],"Music":[8],"is":[9],"a":[10,27,48],"challenging":[11],"task,":[12],"primarily":[13],"due":[14],"to":[15,59],"the":[16],"limited":[17],"availability":[18],"of":[19,36,39],"annotated":[20],"data.":[21],"In":[22],"this":[23],"work,":[24],"we":[25],"propose":[26],"data-efficient":[28],"representation":[29],"learning":[30,54],"framework":[31],"that":[32],"leverages":[33],"large":[34],"amounts":[35],"unannotated":[37],"audio":[38],"music":[41],"performances":[42],"through":[43],"self-supervised":[44],"learning.":[45],"We":[46],"pretrain":[47],"r\u0101ga-independent":[49],"svara":[50,65],"encoder":[51],"using":[52],"contrastive":[53],"on":[55],"pitch":[56],"contours":[57],"augmented":[58],"mimic":[60],"natural":[61],"variations":[62],"human":[64],"renditions.":[66]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
