{"id":"https://openalex.org/W4221151515","doi":"https://doi.org/10.1109/icassp43922.2022.9747612","title":"Improved Singing Voice Separation with Chromagram-Based Pitch-Aware Remixing","display_name":"Improved Singing Voice Separation with Chromagram-Based Pitch-Aware Remixing","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221151515","doi":"https://doi.org/10.1109/icassp43922.2022.9747612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5064396491","display_name":"Siyuan Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyuan Yuan","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102709539","display_name":"Zhepei Wang","orcid":"https://orcid.org/0000-0001-7845-5273"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhepei Wang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036092393","display_name":"Umut Isik","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Umut Isik","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091775011","display_name":"Ritwik Giri","orcid":"https://orcid.org/0000-0002-8599-3229"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ritwik Giri","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021269794","display_name":"Jean-Marc Valin","orcid":"https://orcid.org/0000-0002-9883-6927"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jean-Marc Valin","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082904207","display_name":"Michael M. Goodwin","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Goodwin","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112751528","display_name":"Arvindh Krishnaswamy","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arvindh Krishnaswamy","raw_affiliation_strings":["Amazon Web Services"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Web Services","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3314,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82341832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"115"},"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":0.9993000030517578,"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":0.9976000189781189,"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/singing","display_name":"Singing","score":0.7398636937141418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7235802412033081},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7082281112670898},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6384600400924683},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5855710506439209},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5672245621681213},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2765424847602844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23804783821105957},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10369351506233215}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7398636937141418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7235802412033081},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7082281112670898},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6384600400924683},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5855710506439209},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5672245621681213},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2765424847602844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23804783821105957},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10369351506233215},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/icassp43922.2022.9747612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":25,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W2062710265","https://openalex.org/W2124539664","https://openalex.org/W2669032454","https://openalex.org/W2918803104","https://openalex.org/W2938709889","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2971458685","https://openalex.org/W2972411915","https://openalex.org/W2985214749","https://openalex.org/W3035160371","https://openalex.org/W3097034112","https://openalex.org/W3113792747","https://openalex.org/W3115488976","https://openalex.org/W3133205200","https://openalex.org/W3160733670","https://openalex.org/W4286980120","https://openalex.org/W4298310324","https://openalex.org/W6637992904","https://openalex.org/W6678626330","https://openalex.org/W6766320909","https://openalex.org/W6770592442","https://openalex.org/W6791383405","https://openalex.org/W6801426729"],"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/W2077498359"],"abstract_inverted_index":{"Singing":[0],"voice":[1],"separation":[2],"aims":[3],"to":[4,41],"separate":[5],"music":[6,64],"into":[7],"vocals":[8],"and":[9,48,79],"accompaniment":[10],"components.":[11],"One":[12],"of":[13,24,45],"the":[14,18,21,92],"major":[15],"constraints":[16],"for":[17],"task":[19],"is":[20],"limited":[22],"amount":[23],"training":[25,85],"data":[26,47,57],"with":[27,66,87],"separated":[28],"vocals.":[29],"Data":[30],"augmentation":[31,58],"techniques":[32],"such":[33],"as":[34],"random":[35],"source":[36],"mixing":[37],"have":[38],"been":[39],"shown":[40],"make":[42],"better":[43],"use":[44],"existing":[46],"mildly":[49],"improve":[50],"model":[51],"performance.":[52],"We":[53],"propose":[54],"a":[55],"novel":[56],"technique,":[59],"chromagram-based":[60],"pitch-aware":[61,88],"remixing,":[62],"where":[63],"segments":[65],"high":[67],"pitch":[68],"alignment":[69],"are":[70],"mixed.":[71],"By":[72],"performing":[73],"controlled":[74],"experiments":[75],"in":[76],"both":[77],"supervised":[78],"semi-supervised":[80],"settings,":[81],"we":[82],"demonstrate":[83],"that":[84],"models":[86],"remixing":[89],"significantly":[90],"improves":[91],"test":[93],"signal-to-distortion":[94],"ratio":[95],"(SDR).":[96]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
