{"id":"https://openalex.org/W2518172956","doi":"https://doi.org/10.1109/icme.2016.7552917","title":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","display_name":"Phonetic posteriorgrams for many-to-one voice conversion without parallel data training","publication_year":2016,"publication_date":"2016-07-01","ids":{"openalex":"https://openalex.org/W2518172956","doi":"https://doi.org/10.1109/icme.2016.7552917","mag":"2518172956"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2016.7552917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Multimedia and Expo (ICME)","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/A5019219958","display_name":"Lifa Sun","orcid":null},"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":"Lifa Sun","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377555","display_name":"Kun Li","orcid":"https://orcid.org/0000-0002-6780-4391"},"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":"Kun Li","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704211","display_name":"Hao Wang","orcid":"https://orcid.org/0000-0002-3243-487X"},"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":"Hao Wang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, 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/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":"Shiyin Kang","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"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":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5019219958"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":36.137,"has_fulltext":false,"cited_by_count":316,"citation_normalized_percentile":{"value":0.9971049,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9980999827384949,"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":0.9965000152587891,"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":0.8143613934516907},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7828525304794312},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49301955103874207},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4506072700023651},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44377580285072327},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4409732520580292},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4406415522098541},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43842050433158875},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4347633719444275},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4284370541572571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37189996242523193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143613934516907},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7828525304794312},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49301955103874207},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4506072700023651},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44377580285072327},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4409732520580292},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4406415522098541},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43842050433158875},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4347633719444275},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4284370541572571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37189996242523193},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2016.7552917","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2016.7552917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W304834817","https://openalex.org/W1509691205","https://openalex.org/W1524333225","https://openalex.org/W2032130465","https://openalex.org/W2049686551","https://openalex.org/W2096980176","https://openalex.org/W2115055618","https://openalex.org/W2120605154","https://openalex.org/W2135832479","https://openalex.org/W2156142001","https://openalex.org/W2161476805","https://openalex.org/W2171019095","https://openalex.org/W2294351487","https://openalex.org/W2395403337","https://openalex.org/W2401207139","https://openalex.org/W2404109308","https://openalex.org/W2577042574","https://openalex.org/W3127686677","https://openalex.org/W6603838645","https://openalex.org/W6610843619","https://openalex.org/W6631362777","https://openalex.org/W6696767757","https://openalex.org/W6711872879","https://openalex.org/W6732251480","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,28,48,67,133,145],"novel":[4],"approach":[5,59,120,156],"to":[6,16,53,81,139],"voice":[7],"conversion":[8],"with":[9],"non-parallel":[10],"training":[11,128],"data.":[12],"The":[13,57],"idea":[14],"is":[15,36,79,130],"bridge":[17],"between":[18,85],"speakers":[19],"by":[20],"means":[21],"of":[22,44,63,91],"Phonetic":[23],"PosteriorGrams":[24],"(PPGs)":[25],"obtained":[26],"from":[27,104],"speaker-independent":[29],"automatic":[30],"speech":[31,45,167],"recognition":[32],"(SI-ASR)":[33],"system.":[34],"It":[35],"assumed":[37],"that":[38,154],"these":[39],"PPGs":[40,62,87,103],"can":[41,136],"represent":[42],"articulation":[43],"sounds":[46],"in":[47,165],"speaker-normalized":[49],"space":[50],"and":[51,88,108,169],"correspond":[52],"spoken":[54],"content":[55],"speaker-independently.":[56],"proposed":[58],"first":[60],"obtains":[61],"target":[64,93,147],"speech.":[65,94,118],"Then,":[66],"Deep":[68],"Bidirectional":[69],"Long":[70],"Short-Term":[71],"Memory":[72],"based":[73],"Recurrent":[74],"Neural":[75],"Network":[76],"(DBLSTM)":[77],"structure":[78],"used":[80],"model":[82,135],"the":[83,86,92,105,112],"relationships":[84],"acoustic":[89],"features":[90],"To":[95],"convert":[96],"arbitrary":[97],"source":[98,142],"speech,":[99],"we":[100],"obtain":[101],"its":[102],"same":[106],"SI-ASR":[107],"feed":[109],"them":[110],"into":[111],"trained":[113,134],"DBLSTM":[114],"for":[115,144],"generating":[116],"converted":[117],"Our":[119],"has":[121],"two":[122],"main":[123],"advantages:":[124],"1)":[125],"no":[126],"parallel":[127],"data":[129],"required;":[131],"2)":[132],"be":[137],"applied":[138],"any":[140],"other":[141],"speaker":[143,148,170],"fixed":[146],"(i.e.,":[149],"many-to-one":[150],"conversion).":[151],"Experiments":[152],"show":[153],"our":[155],"performs":[157],"equally":[158],"well":[159],"or":[160],"better":[161],"than":[162],"state-of-the-art":[163],"systems":[164],"both":[166],"quality":[168],"similarity.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":33},{"year":2022,"cited_by_count":41},{"year":2021,"cited_by_count":55},{"year":2020,"cited_by_count":67},{"year":2019,"cited_by_count":48},{"year":2018,"cited_by_count":28},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}