{"id":"https://openalex.org/W3144417991","doi":"https://doi.org/10.1109/icassp43922.2022.9746139","title":"ASSEM-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques","display_name":"ASSEM-VC: Realistic Voice Conversion by Assembling Modern Speech Synthesis Techniques","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3144417991","doi":"https://doi.org/10.1109/icassp43922.2022.9746139","mag":"3144417991"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746139","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":"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/A5072611116","display_name":"Kang-wook Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I2799419483","display_name":"Applied Minds (United States)","ror":"https://ror.org/03szmqd24","country_code":"US","type":"company","lineage":["https://openalex.org/I2799419483"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang-Wook Kim","raw_affiliation_strings":["MINDsLab Inc,Republic of Korea","MINDsLab Inc, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc,Republic of Korea","institution_ids":["https://openalex.org/I2799419483"]},{"raw_affiliation_string":"MINDsLab Inc, Republic of Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044286731","display_name":"Seungwon Park","orcid":"https://orcid.org/0000-0003-3519-7109"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seung-Won Park","raw_affiliation_strings":["Seoul National University,Republic of Korea","Seoul National University, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University,Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National University, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072915273","display_name":"Junhyeok Lee","orcid":"https://orcid.org/0000-0002-4950-5371"},"institutions":[{"id":"https://openalex.org/I2799419483","display_name":"Applied Minds (United States)","ror":"https://ror.org/03szmqd24","country_code":"US","type":"company","lineage":["https://openalex.org/I2799419483"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junhyeok Lee","raw_affiliation_strings":["MINDsLab Inc,Republic of Korea","MINDsLab Inc, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc,Republic of Korea","institution_ids":["https://openalex.org/I2799419483"]},{"raw_affiliation_string":"MINDsLab Inc, Republic of Korea","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003282705","display_name":"Myun-chul Joe","orcid":null},"institutions":[{"id":"https://openalex.org/I2799419483","display_name":"Applied Minds (United States)","ror":"https://ror.org/03szmqd24","country_code":"US","type":"company","lineage":["https://openalex.org/I2799419483"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Myun-Chul Joe","raw_affiliation_strings":["MINDsLab Inc,Republic of Korea","MINDsLab Inc, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MINDsLab Inc,Republic of Korea","institution_ids":["https://openalex.org/I2799419483"]},{"raw_affiliation_string":"MINDsLab Inc, Republic of Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"6997","last_page":"7001"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T10860","display_name":"Speech 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019410371780396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6801360845565796},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6518781185150146},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5310174822807312},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.510003924369812},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.4635685086250305},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13650652766227722},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0832829475402832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019410371780396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6801360845565796},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6518781185150146},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5310174822807312},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.510003924369812},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.4635685086250305},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13650652766227722},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0832829475402832},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/icassp43922.2022.9746139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746139","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":51,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1731081199","https://openalex.org/W2091425152","https://openalex.org/W2171019095","https://openalex.org/W2518172956","https://openalex.org/W2527729766","https://openalex.org/W2545656684","https://openalex.org/W2794490148","https://openalex.org/W2804998325","https://openalex.org/W2885820941","https://openalex.org/W2901254300","https://openalex.org/W2945478979","https://openalex.org/W2949281321","https://openalex.org/W2949382160","https://openalex.org/W2953190524","https://openalex.org/W2963432880","https://openalex.org/W2964243274","https://openalex.org/W2970351109","https://openalex.org/W2972359262","https://openalex.org/W2972473628","https://openalex.org/W2972805867","https://openalex.org/W2972999331","https://openalex.org/W2973154337","https://openalex.org/W2994715919","https://openalex.org/W2995929068","https://openalex.org/W2998572311","https://openalex.org/W3015645837","https://openalex.org/W3015805741","https://openalex.org/W3020570669","https://openalex.org/W3020975377","https://openalex.org/W3030437843","https://openalex.org/W3034794073","https://openalex.org/W3081565196","https://openalex.org/W3092028330","https://openalex.org/W3094635600","https://openalex.org/W3096323553","https://openalex.org/W3096864844","https://openalex.org/W3097001834","https://openalex.org/W3098403858","https://openalex.org/W3102905810","https://openalex.org/W3110041771","https://openalex.org/W6629717138","https://openalex.org/W6637618735","https://openalex.org/W6726528559","https://openalex.org/W6729110096","https://openalex.org/W6761567302","https://openalex.org/W6762533536","https://openalex.org/W6771467084","https://openalex.org/W6772349387","https://openalex.org/W6776390925","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W2021035068","https://openalex.org/W2382821289","https://openalex.org/W2800990999","https://openalex.org/W2554525739","https://openalex.org/W2947571721","https://openalex.org/W2356603089","https://openalex.org/W1607387412","https://openalex.org/W2371908859","https://openalex.org/W2150511655","https://openalex.org/W2142042197"],"abstract_inverted_index":{"Recent":[0],"works":[1],"on":[2,7],"voice":[3],"conversion":[4],"(VC)":[5],"focus":[6],"preserving":[8],"the":[9,12,17,25,48],"rhythm":[10],"and":[11,36,46,66,71,81],"intonation":[13],"as":[14,16],"well":[15],"linguistic":[18],"content.":[19],"To":[20],"preserve":[21],"these":[22],"features":[23,68],"from":[24],"source,":[26],"we":[27],"decompose":[28],"current":[29],"non-parallel":[30,58],"VC":[31,59],"systems":[32],"into":[33],"two":[34],"encoders":[35],"one":[37],"decoder.":[38],"We":[39,61],"analyze":[40],"each":[41],"module":[42],"with":[43,77],"several":[44],"experiments":[45],"reassemble":[47],"best":[49],"components":[50],"to":[51,73],"propose":[52],"Assem-VC,":[53],"a":[54],"new":[55],"state-of-the-art":[56],"any-to-many":[57],"system.":[60],"also":[62],"examine":[63],"that":[64],"PPG":[65],"Cotatron":[67],"are":[69,84],"speaker-dependent,":[70],"attempt":[72],"remove":[74],"speaker":[75],"identity":[76],"adversarial":[78],"training.":[79],"Code":[80],"audio":[82],"samples":[83],"available":[85],"at":[86],"https://github.com/mindslab-ai/assem-vc.":[87]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}