{"id":"https://openalex.org/W4408352866","doi":"https://doi.org/10.1109/icassp49660.2025.10889826","title":"Ultra Lightweight Singing Melody Extraction via Combination of Convolution and MLP","display_name":"Ultra Lightweight Singing Melody Extraction via Combination of Convolution and MLP","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352866","doi":"https://doi.org/10.1109/icassp49660.2025.10889826"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889826","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/A5100361920","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-7193-0622"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Donghua University,School of Comp. Science & Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Comp. Science & Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kangjie Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kangjie Dong","raw_affiliation_strings":["Donghua University,School of Comp. Science & Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Comp. Science & Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045132819","display_name":"Qiubo Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiubo Huang","raw_affiliation_strings":["Donghua University,School of Comp. Science & Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Comp. Science & Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011482849","display_name":"Shuai Yu","orcid":"https://orcid.org/0000-0003-1847-563X"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yu","raw_affiliation_strings":["Donghua University,School of Comp. Science & Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Donghua University,School of Comp. Science & Technology,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100318295","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-8449-3839"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Fudan University,School of Comp. Science & Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,School of Comp. Science & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9958000183105469,"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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":0.9815000295639038,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7686843872070312},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7145179510116577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.68934565782547},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.6703476309776306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.600687563419342},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3270546793937683},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2155504822731018},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10772019624710083},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09911215305328369},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07582777738571167},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.0671364963054657}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7686843872070312},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7145179510116577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.68934565782547},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.6703476309776306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.600687563419342},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3270546793937683},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2155504822731018},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10772019624710083},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09911215305328369},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07582777738571167},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0671364963054657}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889826","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1493535305","https://openalex.org/W1526336542","https://openalex.org/W1967815448","https://openalex.org/W2001426554","https://openalex.org/W2161632835","https://openalex.org/W2296704011","https://openalex.org/W2963158112","https://openalex.org/W2963535133","https://openalex.org/W2964177567","https://openalex.org/W3015608758","https://openalex.org/W3131937837","https://openalex.org/W3191088441","https://openalex.org/W4221161255","https://openalex.org/W4221165769","https://openalex.org/W4224941193","https://openalex.org/W4226297238","https://openalex.org/W4285602366","https://openalex.org/W4310837658","https://openalex.org/W4392909936","https://openalex.org/W4392940320","https://openalex.org/W4393147199","https://openalex.org/W4393158690","https://openalex.org/W4402979596","https://openalex.org/W4403248077","https://openalex.org/W4403792141","https://openalex.org/W6638523607","https://openalex.org/W6714030504","https://openalex.org/W6731524272","https://openalex.org/W6739879593","https://openalex.org/W6743245750","https://openalex.org/W6746836464","https://openalex.org/W6795140394","https://openalex.org/W6800650261","https://openalex.org/W6804925306","https://openalex.org/W6810680386"],"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":{"Singing":[0],"melody":[1,27,82],"extraction":[2,83],"serves":[3],"as":[4],"an":[5,99],"important":[6],"foundation":[7],"in":[8,38,77,143,160],"the":[9,49,78,94,105,110,115,136],"realm":[10],"of":[11,66,80,138],"music":[12],"information":[13],"retrieval":[14],"(MIR).":[15],"Although":[16],"fully":[17],"convolutional":[18,96],"neural":[19],"networks":[20,44],"(CNNs)":[21],"are":[22,30],"commonly":[23],"employed":[24],"for":[25,63],"singing":[26,81],"extraction,":[28],"they":[29],"constrained":[31],"by":[32],"inductive":[33],"biases":[34],"and":[35,121,154,163],"face":[36],"challenges":[37],"establishing":[39],"long":[40],"range":[41],"dependency.":[42],"Transformer-based":[43],"have":[45,60],"better":[46],"performance,":[47],"but":[48],"computational":[50,164],"load":[51],"is":[52],"high.":[53],"Recently,":[54],"many":[55],"multi-layer":[56],"perceptron":[57],"(MLP)":[58],"architectures":[59],"been":[61],"applied":[62],"a":[64,129],"variety":[65],"computer":[67],"vision":[68],"tasks,":[69],"demonstrating":[70],"competitive":[71,169],"performance.":[72,106,170],"However,":[73],"its":[74],"potential":[75],"ability":[76],"task":[79],"remains":[84],"to":[85,118],"be":[86],"further":[87],"explored.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92,108,127],"propose":[93,128],"lightweight":[95,101],"MLP":[97],"(LcMLP),":[98],"ultra":[100],"model":[102,156],"without":[103],"sacrificing":[104],"Firstly,":[107],"improve":[109],"original":[111],"MLP-Mixer.":[112,144],"We":[113,145],"change":[114],"sequential":[116],"MLPs":[117],"parallel":[119],"ones":[120],"add":[122],"some":[123],"skip":[124],"connections.":[125],"Secondly,":[126],"multi-level":[130],"convolution":[131],"fusion":[132],"module":[133],"that":[134],"facilitates":[135],"interaction":[137],"features":[139],"at":[140],"various":[141],"depths":[142],"conducted":[146],"extensive":[147],"experiments":[148],"on":[149],"several":[150],"well-known":[151],"public":[152],"datasets,":[153],"our":[155],"demonstrates":[157],"significant":[158],"advantages":[159],"inference":[161],"speed":[162],"load,":[165],"while":[166],"also":[167],"achieving":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}