{"id":"https://openalex.org/W2939275249","doi":"https://doi.org/10.1109/icassp.2019.8683369","title":"Cross-gender Voice Conversion with Constant F0-Ratio and Average Background Conversion Model","display_name":"Cross-gender Voice Conversion with Constant F0-Ratio and Average Background Conversion Model","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939275249","doi":"https://doi.org/10.1109/icassp.2019.8683369","mag":"2939275249"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5081754443","display_name":"Zbigniew Latka","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131934","display_name":"Lukasiewicz Research Network - Krakow Institute of Technology","ror":"https://ror.org/039bged65","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210129336","https://openalex.org/I4210131934"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Zbigniew Latka","raw_affiliation_strings":["Techmo, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techmo, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I4210131934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077918641","display_name":"Jakub Ga\u0142ka","orcid":"https://orcid.org/0000-0003-1048-8209"},"institutions":[{"id":"https://openalex.org/I4210131934","display_name":"Lukasiewicz Research Network - Krakow Institute of Technology","ror":"https://ror.org/039bged65","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210129336","https://openalex.org/I4210131934"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jakub Galka","raw_affiliation_strings":["Techmo, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techmo, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I4210131934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066410445","display_name":"Bartosz Zi\u00f3\u0142ko","orcid":"https://orcid.org/0000-0001-5485-8879"},"institutions":[{"id":"https://openalex.org/I4210131934","display_name":"Lukasiewicz Research Network - Krakow Institute of Technology","ror":"https://ror.org/039bged65","country_code":"PL","type":"facility","lineage":["https://openalex.org/I4210129336","https://openalex.org/I4210131934"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Bartosz Ziolko","raw_affiliation_strings":["Techmo, Krak\u00f3w, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Techmo, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I4210131934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210131934"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.02655105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"6825","last_page":"6829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9984999895095825,"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":0.991100013256073,"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/mean-opinion-score","display_name":"Mean opinion score","score":0.7540832757949829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7082222104072571},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7049561738967896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6323710680007935},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5611112117767334},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5594543218612671},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4963083863258362},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.49208492040634155},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49000874161720276},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48318567872047424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43869009613990784},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3698110282421112},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3425928056240082},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07922223210334778}],"concepts":[{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.7540832757949829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7082222104072571},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7049561738967896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6323710680007935},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5611112117767334},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5594543218612671},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4963083863258362},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.49208492040634155},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49000874161720276},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48318567872047424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43869009613990784},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3698110282421112},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3425928056240082},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07922223210334778},{"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321042","display_name":"Fundacja na rzecz Nauki Polskiej","ror":"https://ror.org/048zd9m77"},{"id":"https://openalex.org/F4320335039","display_name":"Narodowe Centrum Bada\u0144 i Rozwoju","ror":"https://ror.org/05pwfyy15"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2049686551","https://openalex.org/W2052871313","https://openalex.org/W2118850452","https://openalex.org/W2120605154","https://openalex.org/W2129142580","https://openalex.org/W2168510624","https://openalex.org/W2471520273","https://openalex.org/W2515028311","https://openalex.org/W2519648275","https://openalex.org/W2586453598","https://openalex.org/W2963035245","https://openalex.org/W6684874561"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,19,28,31,43,46,53,56,85,91,96],"method":[4,25],"for":[5,34],"spectral":[6],"voice":[7,36],"conversion":[8,37,49,78,122],"using":[9,69],"parallel":[10],"training":[11],"data.":[12],"The":[13,24,80,109],"proposed":[14,74,86],"solution":[15,87],"was":[16,72],"submitted":[17,94],"to":[18,75,95],"2018":[20,97],"Voice":[21,98],"Conversion":[22,99],"Challenge.":[23],"focuses":[26],"on":[27],"preparation":[29],"of":[30,45,55,66,90,104],"generative":[32],"model":[33,50,60],"cross-gender":[35,77,121],"in":[38,102,120],"differential-filtering":[39],"framework.":[40],"To":[41],"improve":[42,76],"quality":[44,106],"Gaussian":[47],"mixture":[48],"we":[51],"introduced":[52],"usage":[54],"averaged":[57],"speaker":[58],"background":[59],"pre-training":[61],"step.":[62],"Constant":[63],"F0ratio":[64],"transformation":[65],"source":[67],"speech":[68,105],"WORLD":[70],"vocoder":[71],"also":[73],"quality.":[79],"evaluation":[81],"results":[82],"show":[83],"that":[84],"outperforms":[88],"most":[89],"concurrent":[92],"systems":[93],"Challenge,":[100],"both":[101],"terms":[103],"and":[107,115],"similarity.":[108],"system":[110],"achieved":[111],"76%":[112],"similarity":[113],"score":[114,119],"3.22":[116],"mean":[117],"opinion":[118],"task.":[123]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}