{"id":"https://openalex.org/W4410771613","doi":"https://doi.org/10.1109/icasspw65056.2025.11011251","title":"Gamaka Synthesis for Kalpitha Swaras in Carnatic Music","display_name":"Gamaka Synthesis for Kalpitha Swaras in Carnatic Music","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771613","doi":"https://doi.org/10.1109/icasspw65056.2025.11011251"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049029604","display_name":"Raghavasimhan Sankaranarayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghavasimhan Sankaranarayanan","raw_affiliation_strings":["Georgia Institute of Technology,Robotic Musicianship Lab,Atlanta,GA,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Robotic Musicianship Lab,Atlanta,GA,US","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003679010","display_name":"Larry Heck","orcid":"https://orcid.org/0000-0003-3358-6362"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry Heck","raw_affiliation_strings":["Georgia Institute of Technology,AI Virtual Assistant (AVA) Laboratory,Atlanta,GA,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,AI Virtual Assistant (AVA) Laboratory,Atlanta,GA,US","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103010206","display_name":"Gil Weinberg","orcid":"https://orcid.org/0000-0001-5263-2235"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gil Weinberg","raw_affiliation_strings":["Georgia Institute of Technology,Robotic Musicianship Lab,Atlanta,GA,US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Robotic Musicianship Lab,Atlanta,GA,US","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":31.4286,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99191102,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.8944000005722046,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.8944000005722046,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10941","display_name":"Musicology and Musical Analysis","score":0.8378000259399414,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.821399986743927,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.725487232208252},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.383523166179657}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725487232208252},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.383523166179657}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1975163393","https://openalex.org/W1989930111","https://openalex.org/W2026845855","https://openalex.org/W2118774185","https://openalex.org/W2128728535","https://openalex.org/W2169081556","https://openalex.org/W2327678559","https://openalex.org/W2528063314","https://openalex.org/W2556364277","https://openalex.org/W2905554976","https://openalex.org/W2947434216","https://openalex.org/W2962866891","https://openalex.org/W3041591210","https://openalex.org/W3162525687","https://openalex.org/W3169962499","https://openalex.org/W3207845222","https://openalex.org/W4200031395","https://openalex.org/W4251857164","https://openalex.org/W6674386194","https://openalex.org/W6674860338","https://openalex.org/W6703049675","https://openalex.org/W6712540299","https://openalex.org/W6749029207"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Gamaka":[0,79],"(note":[1],"ornamentation)":[2],"is":[3,81,94],"an":[4,70],"essential":[5],"element":[6],"of":[7,21,48,114,135,155,164],"Carnatic":[8,56],"music.":[9],"Earlier":[10],"works":[11],"in":[12,31,55,69,96],"computer-generated":[13,115],"gamakas":[14,156],"focused":[15],"on":[16,111,120,146],"developing":[17],"rule-based":[18],"mathematical":[19],"models":[20],"each":[22],"gamaka,":[23],"which":[24],"fails":[25],"to":[26,167],"capture":[27],"the":[28,46,104,136,147,168],"intricate":[29],"changes":[30],"pitch":[32,86],"and":[33,83,127,129,131,153],"thus":[34],"does":[35],"not":[36],"sound":[37],"natural.":[38],"To":[39],"address":[40],"this":[41,43],"challenge,":[42],"work":[44],"approaches":[45],"synthesis":[47],"gamaka":[49,98],"for":[50,157],"kalpitha":[51],"swaras":[52],"(composed":[53],"notes)":[54],"music":[57],"using":[58,76],"a":[59,142],"data-driven":[60],"system.":[61],"The":[62],"model":[63,93],"uses":[64],"masked":[65],"latent":[66],"space":[67],"representation":[68],"auto-encoder":[71],"architecture":[72],"with":[73,85,99],"features":[74],"extracted":[75,88],"convolutional":[77],"layers.":[78],"information":[80],"embedded":[82],"combined":[84],"contours":[87],"from":[89],"symbolic":[90],"data.":[91],"Our":[92],"successful":[95],"synthesizing":[97],"nuances":[100],"that":[101],"closely":[102],"follow":[103],"ground":[105],"truth.":[106],"We":[107],"evaluated":[108],"our":[109,158],"system":[110],"various":[112],"aspects":[113],"gamakas,":[116],"including":[117],"performance":[118],"scoring":[119],"unseen":[121],"data,":[122],"Turing":[123],"tests,":[124],"new":[125],"phrases":[126],"ragas,":[128],"customizable":[130],"tempo-dependent":[132],"gamakas.":[133],"Results":[134],"expert":[137],"listening":[138],"test":[139],"have":[140],"shown":[141],"26%":[143],"improvement":[144],"(rel.)":[145],"Mean":[148],"Opinion":[149],"Score":[150],"(MOS),":[151],"authenticity,":[152],"intonation":[154],"approach":[159],"-":[160],"(MOS":[161],"3.91":[162],"out":[163],"5)":[165],"compared":[166],"baseline":[169],"(Gaayaka":[170],"Software,":[171],"MOS":[172],"3.1).":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
