{"id":"https://openalex.org/W2739735615","doi":"https://doi.org/10.1587/transinf.2017edl8034","title":"Voice Conversion Using Input-to-Output Highway Networks","display_name":"Voice Conversion Using Input-to-Output Highway Networks","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739735615","doi":"https://doi.org/10.1587/transinf.2017edl8034","mag":"2739735615"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2017edl8034","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edl8034","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/8/E100.D_2017EDL8034/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/8/E100.D_2017EDL8034/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki SAITO","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke TAKAMICHI","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi SARUWATARI","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083394213"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":4.9889,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96147076,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"E100.D","issue":"8","first_page":"1925","last_page":"1928"},"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":0.9986000061035156,"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":0.9937000274658203,"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":0.8407331705093384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6919270753860474},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6729427576065063},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6283537149429321},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6255027055740356},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5954771637916565},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4910552501678467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2338649034500122},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.13301855325698853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407331705093384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6919270753860474},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6729427576065063},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6283537149429321},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6255027055740356},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5954771637916565},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4910552501678467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2338649034500122},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.13301855325698853},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2017edl8034","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edl8034","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/8/E100.D_2017EDL8034/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2017edl8034","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2017edl8034","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E100.D/8/E100.D_2017EDL8034/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5786340949","display_name":null,"funder_award_id":"KAKENHI Grant Number","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7735343334","display_name":"High-quality speech synthesis based on automatically-retrieved speech constraints","funder_award_id":"16H06681","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320321474","display_name":"Cabinet Office, Government of Japan","ror":"https://ror.org/007f5s288"},{"id":"https://openalex.org/F4320322525","display_name":"Secom Science and Technology Foundation","ror":"https://ror.org/05ggzej07"},{"id":"https://openalex.org/F4320325854","display_name":"Council for Science, Technology and Innovation","ror":null},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739735615.pdf","grobid_xml":"https://content.openalex.org/works/W2739735615.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W187033940","https://openalex.org/W1523372075","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2111194146","https://openalex.org/W2111284386","https://openalex.org/W2120605154","https://openalex.org/W2121387787","https://openalex.org/W2130020166","https://openalex.org/W2146502635","https://openalex.org/W2156387975","https://openalex.org/W2194775991","https://openalex.org/W2274854232","https://openalex.org/W2293049663","https://openalex.org/W2331493012","https://openalex.org/W2395578248","https://openalex.org/W2513256765","https://openalex.org/W2658996865","https://openalex.org/W2767767449","https://openalex.org/W3123963976","https://openalex.org/W4395958265"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2939490483","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W2038216521","https://openalex.org/W4385672897","https://openalex.org/W2736574136","https://openalex.org/W1996938627"],"abstract_inverted_index":{"This":[0],"paper":[1,64],"proposes":[2,65],"Deep":[3],"Neural":[4],"Network":[5],"(DNN)-based":[6],"Voice":[7],"Conversion":[8],"(VC)":[9],"using":[10,68],"input-to-output":[11],"highway":[12,69],"networks.":[13],"VC":[14,33,67],"is":[15],"a":[16,66],"speech":[17,26,40,45,101,128],"synthesis":[18],"technique":[19],"that":[20,48,99,116],"converts":[21],"input":[22,44,50,74,87],"features":[23],"into":[24],"output":[25,39,52,89],"parameters,":[27],"and":[28,51,88,130],"DNN-based":[29],"acoustic":[30,78],"models":[31,79],"for":[32],"are":[34,53],"used":[35],"to":[36,75],"estimate":[37],"the":[38,43,49,56,73,81,86,107,117,127,134],"parameters":[41],"from":[42,72],"parameters.":[46,91,111],"Given":[47],"often":[54],"in":[55,61,124],"same":[57],"domain":[58],"(e.g.,":[59],"cepstrum)":[60],"VC,":[62],"this":[63],"networks":[70,123],"connected":[71],"output.":[76],"The":[77,92,112],"predict":[80],"weighted":[82],"spectral":[83,90,110],"differentials":[84],"between":[85],"architecture":[93,119],"not":[94],"only":[95],"alleviates":[96],"over-smoothing":[97],"effects":[98],"degrade":[100],"quality,":[102],"but":[103],"also":[104],"effectively":[105],"represents":[106],"characteristics":[108],"of":[109,126,133],"experimental":[113],"results":[114],"demonstrate":[115],"proposed":[118],"outperforms":[120],"Feed-Forward":[121],"neural":[122],"terms":[125],"quality":[129],"speaker":[131],"individuality":[132],"converted":[135],"speech.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}