{"id":"https:\/\/openalex.org\/W4372260214","doi":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095960","title":"Preserving Background Sound in Noise-Robust Voice Conversion Via Multi-Task Learning","display_name":"Preserving Background Sound in Noise-Robust Voice Conversion Via Multi-Task Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https:\/\/openalex.org\/W4372260214","doi":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095960"},"language":"en","primary_location":{"id":"doi:10.1109\/icassp49357.2023.10095960","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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\/A5015560758","display_name":"Jixun Yao","orcid":"https:\/\/orcid.org\/0000-0002-5324-7360"},"institutions":[{"id":"https:\/\/openalex.org\/I17145004","display_name":"Northwestern Polytechnical University","ror":"https:\/\/ror.org\/01y0j0j86","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jixun Yao","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https:\/\/openalex.org\/I17145004"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5013928267","display_name":"Yi Lei","orcid":"https:\/\/orcid.org\/0000-0002-9256-9311"},"institutions":[{"id":"https:\/\/openalex.org\/I17145004","display_name":"Northwestern Polytechnical University","ror":"https:\/\/ror.org\/01y0j0j86","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Lei","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https:\/\/openalex.org\/I17145004"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5107808955","display_name":"Qing Wang","orcid":"https:\/\/orcid.org\/0009-0008-5449-4815"},"institutions":[{"id":"https:\/\/openalex.org\/I17145004","display_name":"Northwestern Polytechnical University","ror":"https:\/\/ror.org\/01y0j0j86","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https:\/\/openalex.org\/I17145004"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5101783173","display_name":"Pengcheng Guo","orcid":"https:\/\/orcid.org\/0009-0001-2388-5935"},"institutions":[{"id":"https:\/\/openalex.org\/I17145004","display_name":"Northwestern Polytechnical University","ror":"https:\/\/ror.org\/01y0j0j86","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https:\/\/openalex.org\/I17145004"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5081164682","display_name":"Ziqian Ning","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I17145004","display_name":"Northwestern Polytechnical University","ror":"https:\/\/ror.org\/01y0j0j86","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziqian Ning","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https:\/\/openalex.org\/I17145004"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5100668966","display_name":"Lei Xie","orcid":"https:\/\/orcid.org\/0000-0001-8234-0823"},"institutions":[{"id":"https:\/\/openalex.org\/I17145004","display_name":"Northwestern Polytechnical University","ror":"https:\/\/ror.org\/01y0j0j86","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU) School of Computer Science,Xi&#x2019;an,China","institution_ids":["https:\/\/openalex.org\/I17145004"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5101624956","display_name":"Hai Li","orcid":"https:\/\/orcid.org\/0000-0002-1160-3777"},"institutions":[{"id":"https:\/\/openalex.org\/I4210115040","display_name":"iQIYI (China)","ror":"https:\/\/ror.org\/026xvz038","country_code":"CN","type":"company","lineage":["https:\/\/openalex.org\/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Li","raw_affiliation_strings":["iQIYI Inc,China","iQIYI Inc, China"],"affiliations":[{"raw_affiliation_string":"iQIYI Inc,China","institution_ids":["https:\/\/openalex.org\/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https:\/\/openalex.org\/I4210115040"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5100640524","display_name":"Junhui Liu","orcid":"https:\/\/orcid.org\/0000-0003-2259-2273"},"institutions":[{"id":"https:\/\/openalex.org\/I4210115040","display_name":"iQIYI (China)","ror":"https:\/\/ror.org\/026xvz038","country_code":"CN","type":"company","lineage":["https:\/\/openalex.org\/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhui Liu","raw_affiliation_strings":["iQIYI Inc,China","iQIYI Inc, China"],"affiliations":[{"raw_affiliation_string":"iQIYI Inc,China","institution_ids":["https:\/\/openalex.org\/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https:\/\/openalex.org\/I4210115040"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5000506857","display_name":"Danming Xie","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I4210115040","display_name":"iQIYI (China)","ror":"https:\/\/ror.org\/026xvz038","country_code":"CN","type":"company","lineage":["https:\/\/openalex.org\/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danming Xie","raw_affiliation_strings":["iQIYI Inc,China","iQIYI Inc, China"],"affiliations":[{"raw_affiliation_string":"iQIYI Inc,China","institution_ids":["https:\/\/openalex.org\/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https:\/\/openalex.org\/I4210115040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https:\/\/openalex.org\/A5015560758"],"corresponding_institution_ids":["https:\/\/openalex.org\/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.2199,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78600488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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"}},{"id":"https:\/\/openalex.org\/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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\/computer-science","display_name":"Computer science","score":0.7689172625541687},{"id":"https:\/\/openalex.org\/keywords\/source-separation","display_name":"Source separation","score":0.72041916847229},{"id":"https:\/\/openalex.org\/keywords\/distortion","display_name":"Distortion (music)","score":0.6249963045120239},{"id":"https:\/\/openalex.org\/keywords\/speech-recognition","display_name":"Speech recognition","score":0.6184602379798889},{"id":"https:\/\/openalex.org\/keywords\/task","display_name":"Task (project management)","score":0.589945912361145},{"id":"https:\/\/openalex.org\/keywords\/bottleneck","display_name":"Bottleneck","score":0.5419583320617676},{"id":"https:\/\/openalex.org\/keywords\/noise","display_name":"Noise (video)","score":0.5220653414726257},{"id":"https:\/\/openalex.org\/keywords\/multi-task-learning","display_name":"Multi-task learning","score":0.5163101553916931},{"id":"https:\/\/openalex.org\/keywords\/cascade","display_name":"Cascade","score":0.4511895477771759},{"id":"https:\/\/openalex.org\/keywords\/separation","display_name":"Separation (statistics)","score":0.4388728141784668},{"id":"https:\/\/openalex.org\/keywords\/process","display_name":"Process (computing)","score":0.4204624891281128},{"id":"https:\/\/openalex.org\/keywords\/artificial-intelligence","display_name":"Artificial intelligence","score":0.3696545660495758},{"id":"https:\/\/openalex.org\/keywords\/machine-learning","display_name":"Machine learning","score":0.18392717838287354},{"id":"https:\/\/openalex.org\/keywords\/engineering","display_name":"Engineering","score":0.09545600414276123}],"concepts":[{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.7689172625541687},{"id":"https:\/\/openalex.org\/C2776864781","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q52617913","display_name":"Source separation","level":2,"score":0.72041916847229},{"id":"https:\/\/openalex.org\/C126780896","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q899871","display_name":"Distortion (music)","level":4,"score":0.6249963045120239},{"id":"https:\/\/openalex.org\/C28490314","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q189436","display_name":"Speech recognition","level":1,"score":0.6184602379798889},{"id":"https:\/\/openalex.org\/C2780451532","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q759676","display_name":"Task (project management)","level":2,"score":0.589945912361145},{"id":"https:\/\/openalex.org\/C2780513914","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q18210350","display_name":"Bottleneck","level":2,"score":0.5419583320617676},{"id":"https:\/\/openalex.org\/C99498987","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2210247","display_name":"Noise (video)","level":3,"score":0.5220653414726257},{"id":"https:\/\/openalex.org\/C28006648","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5163101553916931},{"id":"https:\/\/openalex.org\/C34146451","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q5048094","display_name":"Cascade","level":2,"score":0.4511895477771759},{"id":"https:\/\/openalex.org\/C2776061190","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4388728141784668},{"id":"https:\/\/openalex.org\/C98045186","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q205663","display_name":"Process (computing)","level":2,"score":0.4204624891281128},{"id":"https:\/\/openalex.org\/C154945302","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3696545660495758},{"id":"https:\/\/openalex.org\/C119857082","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2539","display_name":"Machine learning","level":1,"score":0.18392717838287354},{"id":"https:\/\/openalex.org\/C127413603","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11023","display_name":"Engineering","level":0,"score":0.09545600414276123},{"id":"https:\/\/openalex.org\/C115961682","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q860623","display_name":"Image (mathematics)","level":2,"score":0},{"id":"https:\/\/openalex.org\/C2776257435","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0},{"id":"https:\/\/openalex.org\/C201995342","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q682496","display_name":"Systems engineering","level":1,"score":0},{"id":"https:\/\/openalex.org\/C194257627","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q211554","display_name":"Amplifier","level":3,"score":0},{"id":"https:\/\/openalex.org\/C42360764","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q83588","display_name":"Chemical engineering","level":1,"score":0},{"id":"https:\/\/openalex.org\/C111919701","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q9135","display_name":"Operating system","level":1,"score":0},{"id":"https:\/\/openalex.org\/C31258907","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q1301371","display_name":"Computer network","level":1,"score":0},{"id":"https:\/\/openalex.org\/C149635348","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q193040","display_name":"Embedded system","level":1,"score":0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109\/icassp49357.2023.10095960","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":29,"referenced_works":["https:\/\/openalex.org\/W1552314771","https:\/\/openalex.org\/W2527729766","https:\/\/openalex.org\/W2576309025","https:\/\/openalex.org\/W2907262790","https:\/\/openalex.org\/W3016120385","https:\/\/openalex.org\/W3022057435","https:\/\/openalex.org\/W3081753361","https:\/\/openalex.org\/W3092028330","https:\/\/openalex.org\/W3096090308","https:\/\/openalex.org\/W3096408984","https:\/\/openalex.org\/W3098557217","https:\/\/openalex.org\/W3104309246","https:\/\/openalex.org\/W3163464523","https:\/\/openalex.org\/W3163475957","https:\/\/openalex.org\/W3168719651","https:\/\/openalex.org\/W3197478142","https:\/\/openalex.org\/W3197659778","https:\/\/openalex.org\/W3200209270","https:\/\/openalex.org\/W3206706278","https:\/\/openalex.org\/W4205582447","https:\/\/openalex.org\/W4224916404","https:\/\/openalex.org\/W4226039367","https:\/\/openalex.org\/W4226075807","https:\/\/openalex.org\/W4283836776","https:\/\/openalex.org\/W4298310324","https:\/\/openalex.org\/W6633117090","https:\/\/openalex.org\/W6727697161","https:\/\/openalex.org\/W6783867762","https:\/\/openalex.org\/W6802128655"],"related_works":["https:\/\/openalex.org\/W2595172197","https:\/\/openalex.org\/W2084856301","https:\/\/openalex.org\/W2127970246","https:\/\/openalex.org\/W2885125400","https:\/\/openalex.org\/W1989889224","https:\/\/openalex.org\/W2368461988","https:\/\/openalex.org\/W2077498359","https:\/\/openalex.org\/W4287694193","https:\/\/openalex.org\/W3124278207","https:\/\/openalex.org\/W3046871516"],"abstract_inverted_index":{"Background":[0],"sound":[1,47],"is":[2,9,50],"an":[3,77],"informative":[4],"form":[5],"of":[6],"art":[7],"that":[8,154],"helpful":[10],"in":[11,17,48],"providing":[12],"a":[13,86,91,97,133],"more":[14],"immersive":[15],"experience":[16],"real-application":[18],"voice":[19],"conversion":[20],"(VC)":[21],"scenarios.":[22],"However,":[23],"prior":[24],"research":[25],"about":[26],"VC,":[27],"mainly":[28],"focusing":[29],"on":[30],"clean":[31,176],"voices,":[32],"pay":[33],"rare":[34],"attention":[35],"to":[36,141,170],"VC":[37,49,70,98,126,149,172],"with":[38,175],"background":[39,46],"sound.":[40],"The":[41,120],"critical":[42,107],"problem":[43],"for":[44],"preserving":[45],"inevitable":[51],"speech":[52],"distortion":[53,113],"by":[54,115,138],"the":[55,60,64,69,101,112,116,124,129,143,146,160,171],"neural":[56],"separation":[57,66,88,103,118,122],"model":[58,67],"and":[59,68,96,110,128,148,167],"cascade":[61],"mismatch":[62,144],"between":[63,145],"source":[65,87,102,121],"model.":[71],"In":[72],"this":[73],"paper,":[74],"we":[75],"propose":[76],"end-to-end":[78],"framework":[79,157],"via":[80],"multitask":[81],"learning":[82],"which":[83],"sequentially":[84],"cascades":[85],"(SS)":[89],"module,":[90],"bottleneck":[92],"feature":[93],"extraction":[94],"module":[95],"module.":[99],"Specifically,":[100],"task":[104,127,131],"explicitly":[105],"considers":[106],"phase":[108],"information":[109],"limits":[111],"caused":[114],"imperfect":[117],"process.":[119],"task,":[123],"typical":[125],"unified":[130],"share":[132],"uniform":[134],"reconstruction":[135],"loss":[136],"constrained":[137],"joint":[139],"training":[140],"reduce":[142],"SS":[147],"modules.":[150],"Experimental":[151],"results":[152],"demonstrate":[153],"our":[155],"proposed":[156],"significantly":[158],"outperforms":[159],"baseline":[161],"systems":[162],"while":[163],"achieving":[164],"comparable":[165],"quality":[166],"speaker":[168],"similarity":[169],"models":[173],"trained":[174],"data.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}