{"id":"https://openalex.org/W4392909491","doi":"https://doi.org/10.1109/icassp48485.2024.10445858","title":"Enhancing Note-Level Singing Transcription Model with Unlabeled and Weakly Labeled Data","display_name":"Enhancing Note-Level Singing Transcription Model with Unlabeled and Weakly Labeled Data","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909491","doi":"https://doi.org/10.1109/icassp48485.2024.10445858"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10445858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445858","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":"article","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/A5101263790","display_name":"Yao Qiu","orcid":"https://orcid.org/0009-0009-0276-0904"},"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":true,"raw_author_name":"Yao Qiu","raw_affiliation_strings":["Tencent WeChatAI"],"affiliations":[{"raw_affiliation_string":"Tencent WeChatAI","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076799733","display_name":"Jinchao Zhang","orcid":"https://orcid.org/0000-0002-5279-0468"},"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":"Jinchao Zhang","raw_affiliation_strings":["Tencent WeChatAI"],"affiliations":[{"raw_affiliation_string":"Tencent WeChatAI","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019444889","display_name":"Yong Shan","orcid":"https://orcid.org/0000-0002-3952-9206"},"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":"Yong Shan","raw_affiliation_strings":["Tencent WeChatAI"],"affiliations":[{"raw_affiliation_string":"Tencent WeChatAI","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100770464","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-5899-5165"},"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":"Jie Zhou","raw_affiliation_strings":["Tencent WeChatAI"],"affiliations":[{"raw_affiliation_string":"Tencent WeChatAI","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101263790"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.653424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"345"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9850999712944031,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8866091966629028},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7557867765426636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7552342414855957},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.6029456853866577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5905716419219971},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5435445308685303},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5162832140922546},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4738208055496216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4676591455936432},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4115579426288605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36104220151901245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35263383388519287}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8866091966629028},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7557867765426636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7552342414855957},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.6029456853866577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5905716419219971},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5435445308685303},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5162832140922546},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4738208055496216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4676591455936432},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4115579426288605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36104220151901245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35263383388519287},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10445858","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10445858","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":22,"referenced_works":["https://openalex.org/W86310152","https://openalex.org/W395933519","https://openalex.org/W2294039222","https://openalex.org/W2395579298","https://openalex.org/W2586947700","https://openalex.org/W2635912764","https://openalex.org/W2842511635","https://openalex.org/W3036601975","https://openalex.org/W3041133507","https://openalex.org/W3049247973","https://openalex.org/W3158762648","https://openalex.org/W3160016036","https://openalex.org/W3160649916","https://openalex.org/W3165908916","https://openalex.org/W3167533889","https://openalex.org/W4296068763","https://openalex.org/W4297808394","https://openalex.org/W4311187172","https://openalex.org/W6732421929","https://openalex.org/W6780218876","https://openalex.org/W6781910838","https://openalex.org/W7066299598"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"Note-level":[0],"automatic":[1],"singing":[2,15,79,100],"transcription,":[3],"involving":[4],"the":[5,22,54,108],"extraction":[6],"of":[7,24,143],"onset,":[8],"offset,":[9],"and":[10,53,60,98,102],"pitch":[11],"information":[12],"from":[13,66,95],"a":[14,18,46,67,78,86,119,140],"voice,":[16],"is":[17,58],"crucial":[19],"process":[20,57],"in":[21,32,41],"field":[23,64],"Music":[25],"Information":[26],"Retrieval":[27],"(MIR),":[28],"The":[29,91,111],"recent":[30],"advancements":[31],"deep":[33],"learning":[34],"models":[35],"have":[36],"led":[37],"to":[38,106],"significant":[39,120],"progress":[40],"this":[42,63,74,104],"field.":[43],"However,":[44],"annotating":[45],"training":[47,144],"dataset":[48],"requires":[49],"professional":[50],"music":[51],"expertise,":[52],"entire":[55],"annotation":[56],"time-consuming":[59],"labor-intensive.":[61],"Therefore,":[62],"suffers":[65],"severe":[68],"data":[69,101],"scarcity":[70],"problem.":[71],"To":[72],"address":[73],"issue,":[75],"we":[76],"developed":[77],"transcription":[80,109],"model":[81,92],"based":[82],"on":[83,125],"wav2vec":[84],"2.0,":[85],"pretrained":[87],"speech":[88,97],"representation":[89],"model.":[90],"can":[93],"learn":[94],"unlabeled":[96],"weakly-labeled":[99],"use":[103],"knowledge":[105],"benefit":[107],"task.":[110],"experiments":[112,130],"showed":[113],"that":[114,132],"our":[115,133],"proposed":[116],"method":[117,134],"achieves":[118,135],"improvement":[121],"over":[122],"previous":[123],"approaches":[124],"various":[126],"benchmarks.":[127],"Moreover,":[128],"additional":[129],"demonstrate":[131],"competitive":[136],"performance":[137],"even":[138],"with":[139],"small":[141],"proportion":[142],"data.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}