{"id":"https://openalex.org/W2070242626","doi":"https://doi.org/10.1109/wcsp.2011.6096805","title":"Voice conversion based on style and content separation with dual latent variable model","display_name":"Voice conversion based on style and content separation with dual latent variable model","publication_year":2011,"publication_date":"2011-11-01","ids":{"openalex":"https://openalex.org/W2070242626","doi":"https://doi.org/10.1109/wcsp.2011.6096805","mag":"2070242626"},"language":"en","primary_location":{"id":"doi:10.1109/wcsp.2011.6096805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcsp.2011.6096805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Wireless Communications and Signal Processing (WCSP)","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/A5055340074","display_name":"Xinjian Sun","orcid":"https://orcid.org/0000-0003-2588-9419"},"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":"Xinjian Sun","raw_affiliation_strings":["Institute of Communication Engineering, PLA University of Science & Technology, Nanjing, China","Institute of Communication, Engineering, PLA Univ. of Sci. & Tech., Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Engineering, PLA University of Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Communication, Engineering, PLA Univ. of Sci. & Tech., Nanjing, 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":["Institute of Communication Engineering, PLA University of Science & Technology, Nanjing, China","Institute of Command Automation, PLA Univ. of Sci. & Tech., Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Engineering, PLA University of Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Command Automation, PLA Univ. of Sci. & Tech., Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029308734","display_name":"Jian Sun","orcid":"https://orcid.org/0000-0003-4804-5796"},"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":"Jian Sun","raw_affiliation_strings":["Institute of Communication Engineering, PLA University of Science & Technology, Nanjing, China","Institute of Communication, Engineering, PLA Univ. of Sci. & Tech., Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Engineering, PLA University of Science & Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Institute of Communication, Engineering, PLA Univ. of Sci. & Tech., Nanjing, China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055340074"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1058085,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9843000173568726,"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":0.7038491368293762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6664219498634338},{"id":"https://openalex.org/keywords/bilinear-interpolation","display_name":"Bilinear interpolation","score":0.6181638240814209},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5713990330696106},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5190128087997437},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.4918336868286133},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.4852292537689209},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4481639862060547},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.42851340770721436},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4272863268852234},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.41702917218208313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.360112726688385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3309408724308014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19324368238449097},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0884261429309845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7038491368293762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6664219498634338},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.6181638240814209},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5713990330696106},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5190128087997437},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.4918336868286133},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.4852292537689209},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4481639862060547},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.42851340770721436},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4272863268852234},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.41702917218208313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.360112726688385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3309408724308014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19324368238449097},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0884261429309845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wcsp.2011.6096805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wcsp.2011.6096805","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 International Conference on Wireless Communications and Signal Processing (WCSP)","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":8,"referenced_works":["https://openalex.org/W46528222","https://openalex.org/W2124609748","https://openalex.org/W2125027820","https://openalex.org/W2136111243","https://openalex.org/W2156142001","https://openalex.org/W2166318210","https://openalex.org/W4231951313","https://openalex.org/W6680375596"],"related_works":["https://openalex.org/W2020989338","https://openalex.org/W2147126679","https://openalex.org/W1823617068","https://openalex.org/W4300049944","https://openalex.org/W2115039802","https://openalex.org/W2047528018","https://openalex.org/W2470236000","https://openalex.org/W2097143083","https://openalex.org/W2164147372","https://openalex.org/W2550171623"],"abstract_inverted_index":{"This":[0],"paper":[1,112],"presents":[2],"a":[3],"novel":[4],"method":[5,108],"for":[6,72],"voice":[7,74],"conversion":[8,75,115],"based":[9,122,127],"on":[10,26],"style":[11,45,69],"and":[12,46,57,70,88,95,125],"content":[13,47,71,87],"separation,":[14],"which":[15,49],"is":[16,40,76],"solved":[17],"by":[18,35,79],"using":[19,83],"dual":[20],"latent":[21],"variable":[22],"model":[23],"(D-LVM).":[24],"Based":[25],"D-LVM,":[27],"the":[28,54,58,63,84,89,101,107,111,119],"vocal":[29],"tract":[30],"spectrum":[31],"of":[32,65,68,103],"speech":[33,55,82,86],"represented":[34],"line":[36],"spectral":[37],"frequencies":[38],"(LSF)":[39],"explicitly":[41],"decomposed":[42],"into":[43],"so-called":[44],"factors,":[48],"are":[50],"used":[51],"to":[52,118],"represent":[53],"meaning":[56],"speaker":[59,91],"individuality":[60],"respectively.":[61],"On":[62],"basis":[64],"reasonable":[66],"separation":[67],"speech,":[73],"performed":[77],"successfully":[78],"reproducing":[80],"converted":[81],"initial":[85],"target":[90],"style.":[92],"The":[93],"objective":[94],"subjective":[96],"tests":[97],"show":[98],"that,":[99],"under":[100],"condition":[102],"limited":[104],"training":[105],"dataset,":[106],"proposed":[109],"in":[110],"gets":[113],"better":[114],"performance":[116],"compared":[117],"conventional":[120],"mapping":[121],"GMM":[123],"system":[124],"SVD":[126],"bilinear":[128],"model.":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}