{"id":"https://openalex.org/W3094635600","doi":"https://doi.org/10.21437/interspeech.2020-2412","title":"Transferring Source Style in Non-Parallel Voice Conversion","display_name":"Transferring Source Style in Non-Parallel Voice Conversion","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094635600","doi":"https://doi.org/10.21437/interspeech.2020-2412","mag":"3094635600"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5102778496","display_name":"Songxiang Liu","orcid":"https://orcid.org/0000-0002-0943-2446"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Songxiang Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013296368","display_name":"Yuewen Cao","orcid":"https://orcid.org/0000-0002-1432-161X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Cao","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685461","display_name":"Na Hu","orcid":"https://orcid.org/0000-0001-6362-0969"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Hu","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Tencent, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Tencent, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5102778496"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":2.3861,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91022565,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4721","last_page":"4725"},"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":0.9969000220298767,"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":0.9833999872207642,"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":0.7194176912307739},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6029646396636963},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4110231399536133},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3268895447254181},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.04714709520339966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7194176912307739},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6029646396636963},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4110231399536133},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3268895447254181},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.04714709520339966},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2412","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1509691205","https://openalex.org/W2120605154","https://openalex.org/W2156142001","https://openalex.org/W2176263492","https://openalex.org/W2518172956","https://openalex.org/W2532494225","https://openalex.org/W2774848319","https://openalex.org/W2794490148","https://openalex.org/W2888922217","https://openalex.org/W2889329491","https://openalex.org/W2946200149","https://openalex.org/W2962896155","https://openalex.org/W2963035245","https://openalex.org/W2963539064","https://openalex.org/W2963609956","https://openalex.org/W2963830550","https://openalex.org/W2964069186","https://openalex.org/W2964135678","https://openalex.org/W2964243274","https://openalex.org/W2971753973","https://openalex.org/W2972818416","https://openalex.org/W4298580827"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Voice":[0],"conversion":[1],"(VC)":[2],"techniques":[3],"aim":[4],"to":[5,66,100],"modify":[6],"speaker":[7,38,91],"identity":[8],"of":[9,22,57,80,87,93,105],"an":[10],"utterance":[11],"while":[12],"preserving":[13],"the":[14,23,32,37,55,59,63,67,81,94,102,106],"underlying":[15],"linguistic":[16],"information.Most":[17],"VC":[18,51,83],"approaches":[19],"ignore":[20],"modeling":[21],"speaking":[24,60],"style":[25,61],"(e.g.emotion":[26],"and":[27,39,74,90],"emphasis),":[28],"which":[29,53],"may":[30],"contain":[31],"factors":[33],"intentionally":[34],"added":[35],"by":[36,70],"should":[40],"be":[41],"retained":[42],"during":[43],"conversion.This":[44],"study":[45],"proposes":[46],"a":[47],"sequence-tosequence":[48],"based":[49],"non-parallel":[50],"approach,":[52],"has":[54],"capability":[56],"transferring":[58],"from":[62],"source":[64],"speech":[65,69,88],"converted":[68,95],"explicitly":[71],"modeling.Objective":[72],"evaluation":[73],"subjective":[75],"listening":[76],"tests":[77],"show":[78,101],"superiority":[79],"proposed":[82,107],"approach":[84],"in":[85],"terms":[86],"naturalness":[89],"similarity":[92],"speech.Experiments":[96],"are":[97],"also":[98],"conducted":[99],"source-style":[103],"transferability":[104],"approach.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}