{"id":"https://openalex.org/W4408352211","doi":"https://doi.org/10.1109/icassp49660.2025.10889864","title":"A Singing Melody Extraction Network Via Self-Distillation and Multi-Level Supervision","display_name":"A Singing Melody Extraction Network Via Self-Distillation and Multi-Level Supervision","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352211","doi":"https://doi.org/10.1109/icassp49660.2025.10889864"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ying Hu","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing,Urumqi,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052926836","display_name":"Ju Jing","orcid":"https://orcid.org/0000-0002-8179-3625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiabo Jing","raw_affiliation_strings":["Key Laboratory of Signal Detection and Processing,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Signal Detection and Processing,Urumqi,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055381742","display_name":"Fan Li","orcid":"https://orcid.org/0000-0002-0625-9393"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Li","raw_affiliation_strings":["Xi’an Jiaotong University,School of Information and Communications Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Information and Communications Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070173038","display_name":"Lijun He","orcid":"https://orcid.org/0000-0002-3911-8263"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijun He","raw_affiliation_strings":["Xi’an Jiaotong University,School of Information and Communications Engineering,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,School of Information and Communications Engineering,Xi’an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383305","display_name":"Lin Li","orcid":"https://orcid.org/0009-0006-9691-5556"},"institutions":[{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Lin","raw_affiliation_strings":["Xinjiang Institute of Electronics Research Shares Co., Ltd,Urumgi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang Institute of Electronics Research Shares Co., Ltd,Urumgi,China","institution_ids":["https://openalex.org/I4210110458"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034870160","display_name":"Wenzhong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhong Yang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5042363663"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0507593,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9767000079154968,"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":0.9322999715805054,"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":0.7730236649513245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.697030782699585},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6037778258323669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5678387880325317},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5393104553222656},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14395669102668762},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08010479807853699},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.058432191610336304}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7730236649513245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697030782699585},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6037778258323669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5678387880325317},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5393104553222656},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14395669102668762},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08010479807853699},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.058432191610336304},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1967815448","https://openalex.org/W2001426554","https://openalex.org/W2124539664","https://openalex.org/W2161632835","https://openalex.org/W2194775991","https://openalex.org/W2206275834","https://openalex.org/W2747756448","https://openalex.org/W2963158112","https://openalex.org/W2963535133","https://openalex.org/W3015608758","https://openalex.org/W3131937837","https://openalex.org/W3137609883","https://openalex.org/W3185613252","https://openalex.org/W3190413508","https://openalex.org/W3191088441","https://openalex.org/W3197957534","https://openalex.org/W4206210197","https://openalex.org/W4221165769","https://openalex.org/W4224920338","https://openalex.org/W4285258744","https://openalex.org/W4310837658","https://openalex.org/W4312271884","https://openalex.org/W4312688875","https://openalex.org/W4385822304","https://openalex.org/W4385823161","https://openalex.org/W4390872561","https://openalex.org/W4393159948","https://openalex.org/W4402754092","https://openalex.org/W4403792235","https://openalex.org/W6631190155","https://openalex.org/W6697040288","https://openalex.org/W6714030504","https://openalex.org/W6726497184","https://openalex.org/W6731524272","https://openalex.org/W6756648248","https://openalex.org/W6770515439","https://openalex.org/W6803003856"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Extracting":[0],"singing":[1,23],"melody":[2,24,134],"from":[3,77],"polyphonic":[4],"music":[5,14],"is":[6],"an":[7],"important":[8],"topic":[9],"in":[10,102],"the":[11,38,53,57,74,78,82,99,103,115,168],"field":[12],"of":[13,28,59,110,162],"information":[15,47],"retrieval.":[16],"In":[17,37],"this":[18],"paper,":[19],"we":[20,63],"propose":[21,64],"a":[22,65,107],"extraction":[25,135],"network":[26,90,104],"consisting":[27],"five":[29],"stacked":[30],"multi-scale":[31],"feature":[32,61,75],"time-frequency":[33],"aggregation":[34],"(MF-TFA)":[35],"modules.":[36],"same":[39],"network,":[40],"deeper":[41],"layers":[42,55,117],"generally":[43],"contain":[44],"more":[45,121],"contextual":[46],"than":[48],"shallower":[49,54,83,116],"layers.":[50],"To":[51],"help":[52],"enhance":[56],"ability":[58],"task-relevant":[60,122],"extraction,":[62],"self-distillation":[66],"and":[67,85,137,165,173],"multi-level":[68,86],"supervision":[69,87],"(SD-MS)":[70],"method,":[71,148],"which":[72],"leverages":[73],"distillation":[76],"deepest":[79],"layer":[80,101],"to":[81,88,132],"one":[84],"guide":[89],"training.":[91],"Visualization":[92],"analysis":[93],"shows":[94],"that":[95,129,145],"by":[96],"introducing":[97],"SD-MS,":[98,151],"same-level":[100],"can":[105,118,138],"obtain":[106],"clearer":[108],"representation":[109],"fundamental":[111],"frequency":[112],"components,":[113],"while":[114],"even":[119],"learn":[120],"semantic":[123],"information.":[124],"Ablation":[125],"study":[126],"results":[127,143],"indicate":[128],"SD-MS":[130],"applies":[131],"existing":[133],"models":[136],"consistently":[139],"improve":[140],"performance.":[141],"Experimental":[142],"show":[144],"our":[146],"proposed":[147],"MF-TFA":[149],"with":[150],"outperforms":[152],"six":[153],"compared":[154],"state-of-the-art":[155],"methods,":[156],"achieving":[157],"overall":[158],"accuracy":[159],"(OA)":[160],"scores":[161],"87.1%,":[163],"89.9%,":[164],"76.6%":[166],"on":[167],"ADC":[169],"2004,":[170],"MIREX":[171],"05,":[172],"MEDLEY":[174],"DB":[175],"datasets,":[176],"respectively.":[177],"The":[178],"main":[179],"code":[180],"will":[181],"be":[182],"available":[183],"at":[184],"https://github.com/SmoothJing/MF-TFA_SD-MS.":[185]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}