{"id":"https://openalex.org/W2749881488","doi":"https://doi.org/10.21437/interspeech.2017-488","title":"Direct Modeling of Frequency Spectra and Waveform Generation Based on Phase Recovery for DNN-Based Speech Synthesis","display_name":"Direct Modeling of Frequency Spectra and Waveform Generation Based on Phase Recovery for DNN-Based Speech Synthesis","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2749881488","doi":"https://doi.org/10.21437/interspeech.2017-488","mag":"2749881488"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-488","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5062895056"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":5.9856,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.96874563,"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":"1128","last_page":"1132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7299260497093201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6006194353103638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5986137390136719},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5764060020446777},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4884864091873169},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34984222054481506},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17067208886146545},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11546781659126282}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7299260497093201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6006194353103638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5986137390136719},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5764060020446777},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4884864091873169},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34984222054481506},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17067208886146545},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11546781659126282},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-488","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Takaki, S, Kameoka, H & Yamagishi, J 2017, Direct modeling of frequency spectra and waveform generation based on phase recovery for DNN-based speech synthesis. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 1128-1132, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-488","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f2e9acbe-0ddd-479c-8d9a-e11c5b92cb85","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Takaki, S, Kameoka, H & Yamagishi, J 2017, Direct modeling of frequency spectra and waveform generation based on phase recovery for DNN-based speech synthesis. in Proceedings Interspeech 2017. Interspeech, International Speech Communication Association, pp. 1128-1132, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-488","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1504438288","https://openalex.org/W1927394876","https://openalex.org/W2012086895","https://openalex.org/W2020024436","https://openalex.org/W2049686551","https://openalex.org/W2099471712","https://openalex.org/W2100495367","https://openalex.org/W2102003408","https://openalex.org/W2120847449","https://openalex.org/W2135029798","https://openalex.org/W2145247325","https://openalex.org/W2294797155","https://openalex.org/W2394662942","https://openalex.org/W2395849284","https://openalex.org/W2404881427","https://openalex.org/W2405614646","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2666408839","https://openalex.org/W2746654391","https://openalex.org/W2949382160","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2034702404","https://openalex.org/W2329661839","https://openalex.org/W2353463996","https://openalex.org/W1976234691","https://openalex.org/W4287120475","https://openalex.org/W3171304116","https://openalex.org/W2143160184","https://openalex.org/W2188162781","https://openalex.org/W2051535326","https://openalex.org/W2942163674"],"abstract_inverted_index":{"In":[0,143],"statistical":[1],"parametric":[2],"speech":[3,32,37,120,186],"synthesis":[4],"(SPSS)":[5],"systems":[6],"using":[7,197],"the":[8,28,35,50,66,76,82,112,124,182,198],"high-quality":[9],"vocoder,":[10],"acoustic":[11,162],"features":[12,23],"such":[13,44,55],"as":[14,45,56],"melcepstrum":[15],"coefficients":[16],"and":[17,106,136,164,168,174,189],"F0":[18,155],"are":[19,108,156],"predicted":[20,158],"from":[21,41,154,193],"linguistic":[22],"in":[24],"order":[25],"to":[26,30,64,71,93,114,171],"utilize":[27],"vocoder":[29,125],"generate":[31,175],"waveforms.":[33,176],"However,":[34],"generated":[36,192],"waveform":[38,96,137],"generally":[39],"suffers":[40],"quality":[42],"deterioration":[43],"buzziness":[46,188],"caused":[47],"by":[48],"utilizing":[49],"vocoder.":[51,83,199],"Although":[52],"several":[53],"attempts":[54,92],"improving":[57],"an":[58],"excitation":[59],"model":[60,95,163],"have":[61,89],"been":[62,91,101],"investigated":[63,130],"alleviate":[65],"problem,":[67,87],"it":[68,74],"is":[69,79],"difficult":[70],"completely":[72],"avoid":[73],"if":[75],"SPSS":[77],"system":[78,184,196],"based":[80,139],"on":[81,140],"To":[84],"overcome":[85],"this":[86,144],"there":[88],"recently":[90],"directly":[94,157],"samples.":[97],"Superior":[98],"performance":[99],"has":[100],"demonstrated,":[102],"but":[103],"computation":[104],"time":[105],"latency":[107],"still":[109],"issues.":[110],"With":[111],"aim":[113],"construct":[115],"another":[116],"type":[117],"of":[118,133],"DNN-based":[119,161],"synthesizer":[121],"with":[122],"neither":[123],"nor":[126],"computational":[127],"explosion,":[128],"we":[129,165],"direct":[131],"modeling":[132],"frequency":[134],"spectra":[135],"generation":[138],"phase":[141,173],"recovery.":[142],"framework,":[145],"STFT":[146],"spectral":[147],"amplitudes":[148],"that":[149,181],"include":[150],"harmonics":[151],"information":[152],"derived":[153],"through":[159],"a":[160,194],"use":[166],"Griffin":[167],"Lim\u2019s":[169],"approach":[170],"recover":[172],"The":[177],"experimental":[178],"results":[179],"showed":[180],"proposed":[183],"synthesized":[185],"without":[187],"outperformed":[190],"one":[191],"conventional":[195]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}