{"id":"https://openalex.org/W4408345601","doi":"https://doi.org/10.1109/icassp49660.2025.10889955","title":"HANet: A Harmonic Attention-Based Network for Singing Melody Extraction from Polyphonic Music","display_name":"HANet: A Harmonic Attention-Based Network for Singing Melody Extraction from Polyphonic Music","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345601","doi":"https://doi.org/10.1109/icassp49660.2025.10889955"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889955","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":"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/A5100627215","display_name":"Shijun Wang","orcid":"https://orcid.org/0000-0002-5654-8118"},"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":"Shijun Wang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangzhu Kong","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":"Xiangzhu Kong","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101956433","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0002-6932-6952"},"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":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101575588","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0001-9767-2951"},"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":"Kai Wang","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Computer Science and Technology,Urumqi,China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042363663","display_name":"Ying Hu","orcid":"https://orcid.org/0000-0001-7505-1767"},"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":"Ying Hu","raw_affiliation_strings":["Xinjiang University,School of Computer Science and Technology,Urumqi,China"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9932000041007996,"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":0.9868000149726868,"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/polyphony","display_name":"Polyphony","score":0.9392530918121338},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8107617497444153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.701352596282959},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6719769239425659},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5506165623664856},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4976237118244171},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3807202875614166},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.052228331565856934}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9392530918121338},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8107617497444153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.701352596282959},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6719769239425659},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5506165623664856},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4976237118244171},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3807202875614166},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.052228331565856934},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889955","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/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1493535305","https://openalex.org/W1967815448","https://openalex.org/W2001426554","https://openalex.org/W2149180301","https://openalex.org/W2161632835","https://openalex.org/W2296704011","https://openalex.org/W2747756448","https://openalex.org/W2765459002","https://openalex.org/W2799452163","https://openalex.org/W2938109705","https://openalex.org/W2955058313","https://openalex.org/W2963158112","https://openalex.org/W2963535133","https://openalex.org/W2964177567","https://openalex.org/W3012391395","https://openalex.org/W3131937837","https://openalex.org/W3163379884","https://openalex.org/W3214515055","https://openalex.org/W4211198594","https://openalex.org/W4221165769","https://openalex.org/W4285258744","https://openalex.org/W4290043210","https://openalex.org/W4310837658","https://openalex.org/W4380894123","https://openalex.org/W4385822304","https://openalex.org/W4385823161","https://openalex.org/W4390190098","https://openalex.org/W4396629594","https://openalex.org/W6631190155","https://openalex.org/W6676956424","https://openalex.org/W6697040288","https://openalex.org/W6714030504","https://openalex.org/W6731524272","https://openalex.org/W6746836464"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2807674213"],"abstract_inverted_index":{"Singing":[0],"melody":[1,55,125],"extraction":[2,56],"from":[3,57],"polyphonic":[4,58],"music":[5,13,124],"is":[6,101,161],"a":[7,48,135],"complex":[8],"but":[9,27],"important":[10],"task":[11],"in":[12,24],"information":[14,154],"retrieval.":[15],"Harmonic":[16,49,72],"relationships":[17,85],"have":[18],"been":[19],"shown":[20],"to":[21,38,82,88,103],"be":[22],"crucial":[23],"this":[25],"task,":[26],"most":[28],"existing":[29],"models":[30],"based":[31],"on":[32,121,130],"Convolutional":[33],"Neural":[34],"Networks":[35],"(CNNs)":[36],"struggle":[37],"capture":[39,83],"long-range":[40,106],"harmonic":[41,84,107,153],"dependencies.":[42],"To":[43],"address":[44],"this,":[45],"we":[46],"propose":[47],"Attention-based":[50],"Network":[51],"(HANet)":[52],"for":[53],"singing":[54],"music,":[59],"which":[60],"includes":[61],"multiple":[62,122],"sampling":[63,67],"layers.":[64],"Specifically,":[65],"each":[66],"layer":[68],"uses":[69],"three":[70],"parallel":[71],"Attention":[73,98],"Modules":[74],"(HAMs)":[75],"with":[76,139],"CNNs":[77],"of":[78,137,146],"different":[79],"kernel":[80],"sizes":[81],"across":[86,109],"1":[87],"6":[89],"octaves":[90],"along":[91],"the":[92,96,131,140],"frequency":[93],"axis.":[94],"Additionally,":[95],"Channel":[97],"Module":[99],"(CAM)":[100],"used":[102],"adaptively":[104],"model":[105],"features":[108],"various":[110],"octave":[111,157],"ranges.":[112],"Experimental":[113],"results":[114,149],"show":[115],"that":[116,152],"HANet":[117],"achieves":[118],"state-of-the-art":[119],"performance":[120],"public":[123],"datasets.":[126],"The":[127],"overall":[128],"accuracy":[129],"ADC2004":[132],"dataset":[133],"reached":[134],"peak":[136],"95.2%,":[138],"lowest":[141],"voicing":[142],"false":[143],"alarm":[144],"result":[145],"2.1%.":[147],"Visualization":[148],"directly":[150],"demonstrate":[151],"effectively":[155],"reduces":[156],"errors.":[158],"Our":[159],"code":[160],"available":[162],"online:":[163],"https://github.com/wwsjj/HANet":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}