{"id":"https://openalex.org/W4392903764","doi":"https://doi.org/10.1109/icassp48485.2024.10445818","title":"Humtrans: A Novel Open-Source Dataset for Humming Melody Transcription and Beyond","display_name":"Humtrans: A Novel Open-Source Dataset for Humming Melody Transcription and Beyond","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903764","doi":"https://doi.org/10.1109/icassp48485.2024.10445818"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shansong Liu","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699660","display_name":"Li Xu","orcid":"https://orcid.org/0000-0003-2954-3271"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Li","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675450","display_name":"Dian Li","orcid":"https://orcid.org/0000-0002-7183-0090"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dian Li","raw_affiliation_strings":["Tencent PCG,Foundational Technology Center","Foundational Technology Center, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,Foundational Technology Center","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Foundational Technology Center, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7915","last_page":"7919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hum","display_name":"Hum","score":0.908909797668457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5999670028686523},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5211808085441589},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.4880729913711548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4763087034225464},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4322337508201599},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08406546711921692},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07781803607940674},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.06518217921257019}],"concepts":[{"id":"https://openalex.org/C23161992","wikidata":"https://www.wikidata.org/wiki/Q2922301","display_name":"Hum","level":3,"score":0.908909797668457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5999670028686523},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5211808085441589},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.4880729913711548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4763087034225464},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4322337508201599},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08406546711921692},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07781803607940674},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.06518217921257019},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C554144382","wikidata":"https://www.wikidata.org/wiki/Q213156","display_name":"Performance art","level":2,"score":0.0},{"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:10.1109/icassp48485.2024.10445818","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445818","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1624101316","https://openalex.org/W1970893633","https://openalex.org/W2006386030","https://openalex.org/W2101722322","https://openalex.org/W2104112890","https://openalex.org/W2105143211","https://openalex.org/W2144414181","https://openalex.org/W2149231849","https://openalex.org/W2168103573","https://openalex.org/W2198584637","https://openalex.org/W2593116425","https://openalex.org/W2902303903","https://openalex.org/W2906214917","https://openalex.org/W2981852735","https://openalex.org/W3095303521","https://openalex.org/W3160649916","https://openalex.org/W3165908916","https://openalex.org/W3216284681","https://openalex.org/W4221159539","https://openalex.org/W4288089799","https://openalex.org/W4296068763","https://openalex.org/W4311167650","https://openalex.org/W4372349499","https://openalex.org/W6604048955","https://openalex.org/W6605222893","https://openalex.org/W6607288479","https://openalex.org/W6630420213","https://openalex.org/W6637121078","https://openalex.org/W6703804836","https://openalex.org/W6714030504","https://openalex.org/W6732421929","https://openalex.org/W6762718338","https://openalex.org/W6785764544","https://openalex.org/W6803088475","https://openalex.org/W6811157148","https://openalex.org/W6846414411","https://openalex.org/W6847523890"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W2464878701","https://openalex.org/W4247380401","https://openalex.org/W3013946943","https://openalex.org/W3112683371","https://openalex.org/W3113198510","https://openalex.org/W1918576746","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"the":[3,55,95,120,123,135,158],"HumTrans":[4],"dataset,":[5,65],"which":[6],"is":[7],"publicly":[8],"available":[9],"and":[10,44,146,177,187],"primarily":[11],"designed":[12,102],"for":[13,25,130],"humming":[14,30,64,109,121,161],"melody":[15,31,136,145],"transcription.":[16],"The":[17,108,148,165],"dataset":[18,56,149,162,166],"can":[19],"also":[20],"serve":[21],"as":[22,29],"a":[23,114,127,181],"foundation":[24],"downstream":[26],"tasks":[27],"such":[28],"based":[32],"music":[33,59,76],"generation.":[34],"It":[35],"consists":[36],"of":[37,41,72,88,116,154],"500":[38],"musical":[39,85,128],"compositions":[40],"different":[42],"genres":[43],"languages,":[45],"with":[46,134],"each":[47],"composition":[48],"divided":[49],"into":[50],"multiple":[51],"segments.":[52,60],"In":[53],"total,":[54],"comprises":[57],"1000":[58],"To":[61],"collect":[62],"this":[63],"we":[66,178],"employed":[67],"10":[68],"college":[69],"students,":[70],"all":[71],"whom":[73],"are":[74],"either":[75],"majors":[77],"or":[78],"proficient":[79],"in":[80,142],"playing":[81,138],"at":[82,113],"least":[83],"one":[84],"instrument.":[86],"Each":[87],"them":[89],"hummed":[90],"every":[91],"segment":[92],"twice":[93],"using":[94],"web":[96],"recording":[97],"interface":[98,125],"provided":[99],"by":[100],"our":[101],"website":[103],"<sup":[104,173,190],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[105,174,191],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[106],".":[107,193],"recordings":[110],"were":[111],"sampled":[112],"frequency":[115],"44,100":[117],"Hz.":[118],"During":[119],"session,":[122],"main":[124],"provides":[126],"score":[129],"students":[131],"to":[132,140,163],"reference,":[133],"audio":[137],"simultaneously":[139],"aid":[141],"capturing":[143],"both":[144],"rhythm.":[147],"encompasses":[150],"approximately":[151],"56.22":[152],"hours":[153],"audio,":[155],"making":[156],"it":[157],"largest":[159],"known":[160],"date.":[164],"will":[167,179],"be":[168],"released":[169],"on":[170],"Hugging":[171],"Face":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[175],",":[176],"provide":[180],"GitHub":[182],"repository":[183],"containing":[184],"baseline":[185],"results":[186],"evaluation":[188],"codes":[189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
