{"id":"https://openalex.org/W2997938083","doi":"https://doi.org/10.1109/waspaa.2019.8937135","title":"Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer","display_name":"Joint Singing Pitch Estimation and Voice Separation Based on a Neural Harmonic Structure Renderer","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2997938083","doi":"https://doi.org/10.1109/waspaa.2019.8937135","mag":"2997938083"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu Nakano","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463862","display_name":"Yiming Wu","orcid":"https://orcid.org/0000-0003-1388-7192"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yiming Wu","raw_affiliation_strings":["Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025832278","display_name":"Ryo Nishikimi","orcid":"https://orcid.org/0000-0002-3638-6115"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Nishikimi","raw_affiliation_strings":["Kyoto University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055656287","display_name":"Kin Wah Edward Lin","orcid":"https://orcid.org/0000-0001-6749-6889"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kin Wah Edward Lin","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"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":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"160","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7654730081558228},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7119081616401672},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7025653123855591},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6324371099472046},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6290984153747559},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6203550100326538},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.5972179174423218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5652828216552734},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.515110433101654},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5144579410552979},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48411500453948975},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4763205945491791},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4730980694293976},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.44448399543762207},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4168829023838043},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23009410500526428},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06906643509864807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7654730081558228},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7119081616401672},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7025653123855591},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6324371099472046},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6290984153747559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6203550100326538},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5972179174423218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5652828216552734},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.515110433101654},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5144579410552979},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48411500453948975},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4763205945491791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4730980694293976},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.44448399543762207},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4168829023838043},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23009410500526428},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06906643509864807},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/waspaa.2019.8937135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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":47,"referenced_works":["https://openalex.org/W1519655822","https://openalex.org/W1522301498","https://openalex.org/W1578924114","https://openalex.org/W1594771616","https://openalex.org/W1901129140","https://openalex.org/W2116244429","https://openalex.org/W2130770109","https://openalex.org/W2161632835","https://openalex.org/W2296724634","https://openalex.org/W2405258286","https://openalex.org/W2407685581","https://openalex.org/W2506203739","https://openalex.org/W2516392987","https://openalex.org/W2516857479","https://openalex.org/W2552071709","https://openalex.org/W2577202280","https://openalex.org/W2767071179","https://openalex.org/W2773294482","https://openalex.org/W2774707525","https://openalex.org/W2796571515","https://openalex.org/W2902480954","https://openalex.org/W2902796839","https://openalex.org/W2902808043","https://openalex.org/W2920728711","https://openalex.org/W2963249619","https://openalex.org/W2963452667","https://openalex.org/W2963527086","https://openalex.org/W2963750251","https://openalex.org/W2964121744","https://openalex.org/W6631117800","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6697040288","https://openalex.org/W6713676406","https://openalex.org/W6714030504","https://openalex.org/W6724896095","https://openalex.org/W6726277037","https://openalex.org/W6729728456","https://openalex.org/W6732421929","https://openalex.org/W6746836464","https://openalex.org/W6746914816","https://openalex.org/W6749858131","https://openalex.org/W6751512325","https://openalex.org/W6756560125","https://openalex.org/W6756648248","https://openalex.org/W6756710279","https://openalex.org/W6760299066"],"related_works":["https://openalex.org/W3094316140","https://openalex.org/W3133205200","https://openalex.org/W4289363934","https://openalex.org/W2898145319","https://openalex.org/W2098101267","https://openalex.org/W2898606530","https://openalex.org/W2059119686","https://openalex.org/W4289362680","https://openalex.org/W2403380333","https://openalex.org/W2761596192"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,56,62,68,79,102,121],"multi-task":[4],"learning":[5],"approach":[6],"to":[7,54,151],"joint":[8],"extraction":[9,49,188],"(fundamental":[10],"frequency":[11],"(F0)":[12],"estimation)":[13],"and":[14,50,78,92,189],"separation":[15,51],"of":[16,44,67,117,120,127,155],"singing":[17,122],"voices":[18],"from":[19],"music":[20],"signals.":[21],"While":[22],"deep":[23,45,69],"neural":[24,71],"networks":[25,99,185],"have":[26,35,55],"been":[27,37],"used":[28,143],"successfully":[29],"for":[30,73,89,146,158,186],"each":[31],"task,":[32],"both":[33],"tasks":[34],"not":[36],"dealt":[38],"with":[39,81],"simultaneously":[40],"in":[41,133],"the":[42,115,134,152,156,177,182],"context":[43],"learning.":[46],"Since":[47],"vocal":[48,74,91,187],"are":[52,140],"considered":[53],"mutually":[57],"beneficial":[58],"relationship,":[59],"we":[60,100],"propose":[61],"unified":[63,179],"network":[64,72,135,166,180],"that":[65,105,176],"consists":[66],"convolutional":[70],"F0":[75,108],"saliency":[76,109],"estimation":[77],"U-Net":[80,157],"an":[82,107],"encoder":[83],"shared":[84],"by":[85,171],"two":[86,98],"decoders":[87],"specialized":[88],"separating":[90],"accompaniment":[93],"parts,":[94],"respectively.":[95],"Between":[96],"these":[97],"introduce":[101],"differentiable":[103],"layer":[104],"converts":[106],"spectrogram":[110],"into":[111],"harmonic":[112,118,128,138],"masks":[113,139,149],"indicating":[114],"locations":[116],"partials":[119],"voice.":[123],"The":[124,137,164],"physical":[125],"meaning":[126],"structure":[129],"is":[130],"thus":[131],"reflected":[132],"architecture.":[136],"then":[141],"effectively":[142],"as":[144],"scaffolds":[145],"estimating":[147],"fine-structured":[148],"thanks":[150],"excellent":[153],"capability":[154],"domain-preserving":[159],"conversion":[160],"(e.g.,":[161],"image-to-image":[162],"conversion).":[163],"whole":[165],"can":[167],"be":[168],"trained":[169],"jointly":[170],"backpropagation.":[172],"Experimental":[173],"results":[174],"showed":[175],"proposed":[178],"outperformed":[181],"conventional":[183],"independent":[184],"separation.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}