{"id":"https://openalex.org/W2786868129","doi":"https://doi.org/10.1109/asru.2017.8269007","title":"An investigation of multi-speaker training for wavenet vocoder","display_name":"An investigation of multi-speaker training for wavenet vocoder","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786868129","doi":"https://doi.org/10.1109/asru.2017.8269007","mag":"2786868129"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8269007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269007","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039826522","display_name":"Akira Tamamori","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Tamamori","raw_affiliation_strings":["Institute of Innovation for Future Society, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Innovation for Future Society, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037417355","display_name":"Kazuhiro Kobayashi","orcid":"https://orcid.org/0000-0001-7801-147X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kobayashi","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Graduate School of Information Science, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"712","last_page":"718"},"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":0.9988999962806702,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914082407951355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7623974084854126},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5427489876747131},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.43825122714042664},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07665148377418518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914082407951355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7623974084854126},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5427489876747131},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.43825122714042664},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07665148377418518},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8269007","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269007","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5099999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1963637322","https://openalex.org/W2009674825","https://openalex.org/W2039800941","https://openalex.org/W2046104252","https://openalex.org/W2049686551","https://openalex.org/W2074783531","https://openalex.org/W2111284386","https://openalex.org/W2129343891","https://openalex.org/W2131062138","https://openalex.org/W2145892079","https://openalex.org/W2150658333","https://openalex.org/W2152205330","https://openalex.org/W2428180336","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2556247670","https://openalex.org/W2749651610","https://openalex.org/W2759925408","https://openalex.org/W2907162034","https://openalex.org/W2964121744","https://openalex.org/W4235716345","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2039489009"],"abstract_inverted_index":{"In":[0,13],"this":[1],"paper,":[2],"we":[3,17,91],"investigate":[4,101],"the":[5,77,85,97,110,135,142],"effectiveness":[6],"of":[7,38,73,87,146],"multi-speaker":[8,93,136],"training":[9,94,137],"for":[10,140],"WaveNet":[11,25,89,98,112,143],"vocoder.":[12],"our":[14,21],"previous":[15],"work,":[16],"have":[18],"demonstrated":[19],"that":[20,108],"proposed":[22],"speaker-dependent":[23,82],"(SD)":[24],"vocoder,":[26,62,90],"which":[27],"is":[28,36,66,124,138],"trained":[29],"with":[30],"a":[31],"single":[32],"speaker's":[33],"speech":[34,147],"data,":[35],"capable":[37,145],"modeling":[39],"temporal":[40],"waveform":[41],"structure,":[42],"such":[43],"as":[44],"phase":[45],"information,":[46],"and":[47,100,133],"makes":[48],"it":[49,65,123],"possible":[50],"to":[51,59,69,80,96,126],"generate":[52,70],"more":[53],"naturally":[54],"sounding":[55],"synthetic":[56,71],"voices":[57,72,121],"compared":[58],"conventional":[60],"high-quality":[61],"STRAIGHT.":[63],"However,":[64],"still":[67,114],"difficult":[68],"various":[74],"speakers":[75],"using":[76],"SD-WaveNet":[78],"due":[79],"its":[81,102],"property.":[83],"Towards":[84],"development":[86],"speaker-independent":[88],"apply":[92],"techniques":[95],"vocoder":[99,113,144],"effectiveness.":[103],"The":[104],"experimental":[105],"results":[106],"demonstrate":[107],"1)":[109],"multispeaker":[111],"outperforms":[115],"STRAIGHT":[116,127],"in":[117,128],"generating":[118,129],"known":[119],"speakers'":[120,131],"but":[122],"comparable":[125],"unknown":[130],"voices,":[132],"2)":[134],"effective":[139],"developing":[141],"modification.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":32},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":23}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}