{"id":"https://openalex.org/W4392285990","doi":"https://doi.org/10.1007/s40747-024-01375-6","title":"A noise-robust voice conversion method with controllable background sounds","display_name":"A noise-robust voice conversion method with controllable background sounds","publication_year":2024,"publication_date":"2024-02-29","ids":{"openalex":"https://openalex.org/W4392285990","doi":"https://doi.org/10.1007/s40747-024-01375-6"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01375-6","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s40747-024-01375-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01375-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01375-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101452655","display_name":"Lele Chen","orcid":"https://orcid.org/0000-0002-7073-0450"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lele Chen","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China"],"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011581435","display_name":"Xiongwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongwei Zhang","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China"],"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100630215","display_name":"Yihao Li","orcid":"https://orcid.org/0000-0002-5271-1395"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Li","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China"],"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085248515","display_name":"Meng Sun","orcid":"https://orcid.org/0000-0002-7435-3752"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Sun","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China"],"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100367141","display_name":"Weiwei Chen","orcid":"https://orcid.org/0000-0003-3359-0556"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwei Chen","raw_affiliation_strings":["College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China"],"affiliations":[{"raw_affiliation_string":"College of Command and Control Engineering, Army Engineering University of PLA, Nanjing, 210007, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101452655"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.3415,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47419457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":"3","first_page":"3981","last_page":"3994"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9950000047683716,"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":0.776761531829834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7635016441345215},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5069130063056946},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.49338260293006897},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4851308763027191},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.48118430376052856},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47345513105392456},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4715585708618164},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.435986191034317},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42600560188293457},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3473803699016571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2850521504878998},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0770784318447113}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.776761531829834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7635016441345215},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5069130063056946},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.49338260293006897},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4851308763027191},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.48118430376052856},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47345513105392456},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4715585708618164},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.435986191034317},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42600560188293457},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3473803699016571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2850521504878998},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0770784318447113},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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":2,"locations":[{"id":"doi:10.1007/s40747-024-01375-6","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s40747-024-01375-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01375-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7aa48dec97f54bab9a1585965cf39cdd","is_oa":true,"landing_page_url":"https://doaj.org/article/7aa48dec97f54bab9a1585965cf39cdd","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 3, Pp 3981-3994 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01375-6","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1007/s40747-024-01375-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01375-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1122468876","display_name":null,"funder_award_id":"BK20180080","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3075762026","display_name":null,"funder_award_id":"BK20180080","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3800968795","display_name":null,"funder_award_id":"62371469","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3910829908","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G3961884915","display_name":null,"funder_award_id":"2018008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4514102772","display_name":null,"funder_award_id":"62071484","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6806802732","display_name":null,"funder_award_id":"BK2018","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8458776083","display_name":null,"funder_award_id":"62071484","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392285990.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W2141998673","https://openalex.org/W2576309025","https://openalex.org/W2902070858","https://openalex.org/W2939131199","https://openalex.org/W2943554574","https://openalex.org/W2963341071","https://openalex.org/W2972659941","https://openalex.org/W2998832642","https://openalex.org/W3015219411","https://openalex.org/W3015434413","https://openalex.org/W3018201762","https://openalex.org/W3088108644","https://openalex.org/W3096408984","https://openalex.org/W3098557217","https://openalex.org/W3101528112","https://openalex.org/W3102190437","https://openalex.org/W3107080137","https://openalex.org/W3113497772","https://openalex.org/W3117936886","https://openalex.org/W3162414783","https://openalex.org/W3163271138","https://openalex.org/W3163983014","https://openalex.org/W3197042120","https://openalex.org/W3197659778","https://openalex.org/W3208709726","https://openalex.org/W4205582447","https://openalex.org/W4212963009","https://openalex.org/W4226039367","https://openalex.org/W4283015658","https://openalex.org/W4295895242","https://openalex.org/W4319934140","https://openalex.org/W4372260214","https://openalex.org/W4385337322","https://openalex.org/W6601215111"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2135485548","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W2124849039","https://openalex.org/W2851491717"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"noises":[2],"are":[3,152,211],"usually":[4,26],"treated":[5],"as":[6],"redundant":[7],"or":[8,72],"even":[9],"harmful":[10],"to":[11,28,33,40,44,70,73,107,133,167],"voice":[12,60,127,149],"conversion.":[13,35],"Therefore,":[14],"when":[15],"converting":[16],"noisy":[17],"speech,":[18],"a":[19,58,66,80,85,126,156],"pretrained":[20],"module":[21,50,83,104,129,151],"of":[22,207],"speech":[23,31,41,81,96,114,138,141,146,173,202,210],"separation":[24,49,82,142,147],"is":[25,63,88,105],"deployed":[27],"estimate":[29],"clean":[30,137],"prior":[32],"the":[34,45,48,52,75,94,98,109,112,116,135,140,145,169,183,198,208],"However,":[36],"this":[37,56],"can":[38,68],"lead":[39],"distortion":[42],"due":[43],"mismatch":[46],"between":[47,111],"and":[51,97,115,148,162,176,192,204,213],"conversion":[53,61,128,150],"one.":[54],"In":[55],"paper,":[57],"noise-robust":[59],"model":[62,185],"proposed,":[64,89],"where":[65,90],"user":[67],"choose":[69],"retain":[71],"remove":[74],"background":[76,99,117],"sounds":[77,118],"freely.":[78],"Firstly,":[79],"with":[84,130,197],"dual-decoder":[86],"structure":[87],"two":[91],"decoders":[92],"decode":[93],"denoised":[95,113],"sounds,":[100],"respectively.":[101,215],"A":[102],"bridge":[103],"used":[106],"capture":[108],"interactions":[110],"in":[119,189],"parallel":[120],"layers":[121],"through":[122],"information":[123,164],"exchanging.":[124],"Subsequently,":[125],"multiple":[131],"encoders":[132],"convert":[134],"estimated":[136],"from":[139],"model.":[143],"Finally,":[144],"jointly":[153],"trained":[154],"using":[155],"loss":[157,161],"function":[158],"combining":[159],"cycle":[160],"mutual":[163],"loss,":[165],"aiming":[166],"improve":[168],"decoupling":[170],"efficacy":[171],"among":[172],"contents,":[174],"pitch,":[175],"speaker":[177,205],"identity.":[178],"Experimental":[179],"results":[180],"show":[181],"that":[182],"proposed":[184],"obtains":[186],"significant":[187],"improvements":[188],"both":[190],"subjective":[191],"objective":[193],"evaluation":[194],"metrics":[195],"compared":[196],"existing":[199],"baselines.":[200],"The":[201],"naturalness":[203],"similarity":[206],"converted":[209],"3.47":[212],"3.43,":[214]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}