{"id":"https://openalex.org/W4392909572","doi":"https://doi.org/10.1109/icassp48485.2024.10446245","title":"Resource-Constrained Stereo Singing Voice Cancellation","display_name":"Resource-Constrained Stereo Singing Voice Cancellation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909572","doi":"https://doi.org/10.1109/icassp48485.2024.10446245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446245","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5052641101","display_name":"Clara Borrelli","orcid":"https://orcid.org/0000-0002-8127-9976"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Clara Borrelli","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057121270","display_name":"James Rae","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Rae","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057843247","display_name":"Do\u011fa\u00e7 Ba\u015faran","orcid":"https://orcid.org/0000-0003-2535-8239"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dogac Basaran","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017327131","display_name":"Matt McVicar","orcid":"https://orcid.org/0000-0003-0212-4093"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matt McVicar","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041575981","display_name":"Mehrez Souden","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mehrez Souden","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067270556","display_name":"Matthias Mauch","orcid":"https://orcid.org/0000-0002-4352-6809"},"institutions":[{"id":"https://openalex.org/I4210107260","display_name":"Apple (United Kingdom)","ror":"https://ror.org/01vpeym60","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210107260"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthias Mauch","raw_affiliation_strings":["Apple"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Apple","institution_ids":["https://openalex.org/I4210107260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210107260"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"436","last_page":"440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9854000210762024,"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":0.9854000210762024,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9786999821662903,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9402999877929688,"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":0.7925539612770081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7371612787246704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.589069664478302},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19127234816551208}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7925539612770081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371612787246704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.589069664478302},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19127234816551208},{"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/icassp48485.2024.10446245","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446245","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/W1522301498","https://openalex.org/W1998643818","https://openalex.org/W2040490772","https://openalex.org/W2047102900","https://openalex.org/W2565807767","https://openalex.org/W2790729248","https://openalex.org/W2937484199","https://openalex.org/W2952218014","https://openalex.org/W2964058413","https://openalex.org/W2990594533","https://openalex.org/W3001377302","https://openalex.org/W3015753416","https://openalex.org/W3037149862","https://openalex.org/W3090496396","https://openalex.org/W3099330747","https://openalex.org/W3162801840","https://openalex.org/W3213726885","https://openalex.org/W4205247735","https://openalex.org/W4285108271","https://openalex.org/W4372260250","https://openalex.org/W4375928773","https://openalex.org/W6631190155","https://openalex.org/W6751512325","https://openalex.org/W6783557883","https://openalex.org/W6784335252"],"related_works":["https://openalex.org/W4391375266","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","https://openalex.org/W2366077683"],"abstract_inverted_index":{"We":[0,27],"study":[1],"the":[2,97,103,134],"problem":[3],"of":[4,11,136],"stereo":[5,25,84,106],"singing":[6,62],"voice":[7,63],"cancellation,":[8],"a":[9,24,42,51,105,111,129],"subtask":[10],"music":[12],"source":[13,37],"separation,":[14],"whose":[15],"goal":[16],"is":[17,53,74,122],"to":[18,30,34,66,82],"estimate":[19],"an":[20,78],"instrumental":[21],"background":[22],"from":[23,41],"mix.":[26],"explore":[28],"how":[29],"achieve":[31],"performance":[32],"similar":[33],"large":[35],"state-of-the-art":[36],"separation":[38],"networks":[39],"starting":[40],"small,":[43],"efficient":[44],"model":[45,52,81,93,107],"for":[46],"real-time":[47],"speech":[48],"separation.":[49],"Such":[50],"useful":[54],"when":[55],"memory":[56],"and":[57,61,95,128],"compute":[58],"are":[59,89],"limited":[60,69],"processing":[64],"has":[65],"run":[67],"with":[68],"look-ahead.":[70],"In":[71],"practice,":[72],"this":[73],"realised":[75],"by":[76,91,109],"adapting":[77],"existing":[79],"mono":[80],"handle":[83],"input.":[85],"Improvements":[86],"in":[87,139],"quality":[88],"obtained":[90],"tuning":[92],"parameters":[94],"expanding":[96],"training":[98],"set.":[99],"Moreover,":[100],"we":[101],"highlight":[102],"benefits":[104],"brings":[108],"introducing":[110],"new":[112],"metric":[113],"which":[114],"detects":[115],"attenuation":[116],"inconsistencies":[117],"between":[118],"channels.":[119],"Our":[120],"approach":[121],"evaluated":[123],"using":[124],"objective":[125],"offline":[126],"metrics":[127],"large-scale":[130],"MUSHRA":[131],"trial,":[132],"confirming":[133],"effectiveness":[135],"our":[137],"techniques":[138],"stringent":[140],"listening":[141],"tests.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}