{"id":"https://openalex.org/W4388189390","doi":"https://doi.org/10.1145/3625135.3625137","title":"An Algorithmic Approach to Automated Symbolic Transcription of Hindustani Vocals","display_name":"An Algorithmic Approach to Automated Symbolic Transcription of Hindustani Vocals","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4388189390","doi":"https://doi.org/10.1145/3625135.3625137"},"language":"en","primary_location":{"id":"doi:10.1145/3625135.3625137","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625135.3625137","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625135.3625137","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 10th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3625135.3625137","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053030141","display_name":"Rachit Kumar Jain","orcid":"https://orcid.org/0009-0008-7786-5316"},"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":true,"raw_author_name":"Rhythm Jain","raw_affiliation_strings":["School of Music, Georgia Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0009-0008-7786-5316","affiliations":[{"raw_affiliation_string":"School of Music, Georgia Institute of Technology, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030988830","display_name":"Claire Arthur","orcid":"https://orcid.org/0000-0002-5454-8384"},"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":"Claire Arthur","raw_affiliation_strings":["School of Music, Georgia Institute of Technology, United States"],"raw_orcid":"https://orcid.org/0000-0002-5454-8384","affiliations":[{"raw_affiliation_string":"School of Music, Georgia Institute of Technology, United States","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053030141"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.1919,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45849582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9975000023841858,"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":0.9969000220298767,"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/transcription","display_name":"Transcription (linguistics)","score":0.6691539287567139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5718140006065369},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4568735659122467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4195743203163147},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3628867566585541},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.362186998128891},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14485478401184082},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11983111500740051}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6691539287567139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5718140006065369},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4568735659122467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4195743203163147},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3628867566585541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.362186998128891},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14485478401184082},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11983111500740051},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625135.3625137","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625135.3625137","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625135.3625137","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 10th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3625135.3625137","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625135.3625137","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625135.3625137","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 10th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4388189390.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W1972320119","https://openalex.org/W1976069042","https://openalex.org/W2093219062","https://openalex.org/W2096916483","https://openalex.org/W2110251754","https://openalex.org/W2127566601","https://openalex.org/W2157850652","https://openalex.org/W2258376792","https://openalex.org/W2338890634","https://openalex.org/W2605213159","https://openalex.org/W2609545421","https://openalex.org/W2732388586","https://openalex.org/W2774585603","https://openalex.org/W2893905608","https://openalex.org/W2906214917","https://openalex.org/W2914859903","https://openalex.org/W2939425477","https://openalex.org/W3035609550","https://openalex.org/W3044620871","https://openalex.org/W3103962866","https://openalex.org/W3152594694","https://openalex.org/W3182575357","https://openalex.org/W4200456473","https://openalex.org/W4225281045","https://openalex.org/W4312552420"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W4388145910","https://openalex.org/W2381570729","https://openalex.org/W1976205134","https://openalex.org/W4248336175","https://openalex.org/W2031260042","https://openalex.org/W2391445434","https://openalex.org/W3204019825","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Although":[0],"a":[1,54,62,67,88,112],"sizable":[2],"body":[3],"of":[4,33,36,48,90,104,115],"digital":[5],"music":[6,39,73,121,157],"scholarship":[7],"has":[8,14],"focused":[9],"on":[10,87],"automatic":[11,156],"transcription,":[12],"it":[13,192],"almost":[15],"exclusively":[16],"been":[17],"applied":[18],"to":[19,29,52,61,66,100,142,144,166,174],"Western":[20],"music.":[21],"In":[22,75,98],"this":[23,132],"paper,":[24],"we":[25,110,160,178],"outline":[26],"an":[27],"algorithm":[28,50,78,141,159],"automate":[30],"the":[31,59,91,102,134,139,162,172,180],"transcription":[32,158],"vocal":[34],"performances":[35],"Hindust\u0101ni":[37,116,120,125],"classical":[38],"(HCM)":[40],"from":[41,151],"fundamental":[42],"frequency":[43],"(f0)":[44],"contours.":[45],"The":[46],"goal":[47],"our":[49,77,105,130,155],"is":[51,133],"output":[53,183],"symbolic":[55],"representation":[56],"that":[57],"reduces":[58],"performance":[60,103],"high-level":[63],"syntactic":[64],"construct\u2014akin":[65],"musical":[68],"score\u2014for":[69],"use":[70,161],"in":[71,96,124,187],"computational":[72],"analysis.":[74],"particular,":[76],"not":[79],"only":[80],"transcribes":[81],"notes":[82,148,169],"but":[83],"also":[84],"ornamentation,":[85,117],"focusing":[86],"subset":[89],"most":[92],"common":[93],"ornamentation":[94,106,150],"types":[95],"HCM.":[97],"order":[99],"evaluate":[101,154,167,175],"detection":[107],"and":[108,138,149,171,185,190],"classification,":[109],"created":[111],"small":[113],"dataset":[114,164],"labeled":[118],"by":[119],"experts:":[122],"Ornamentation":[123],"Vocals":[126],"(OHV)":[127],"dataset.":[128],"To":[129,153],"knowledge,":[131],"first":[135,140],"such":[136],"dataset,":[137],"attempt":[143],"automatically":[145],"transcribe":[146,179],"both":[147],"vocals.":[152],"Saraga":[163],"[39]":[165],"stable":[168],"(swara),":[170],"OHV":[173],"ornamentation.":[176],"Finally,":[177],"entire":[181],"aggregate":[182],"(notes":[184],"ornamentation)":[186],"humdrum":[188],"format":[189],"make":[191],"available":[193],"publicly.":[194],"Remaining":[195],"challenges":[196],"for":[197],"future":[198],"research":[199],"are":[200],"discussed.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}