{"id":"https://openalex.org/W3107904486","doi":"https://doi.org/10.1587/transinf.2020edp7075","title":"DNN-Based Full-Band Speech Synthesis Using GMM Approximation of Spectral Envelope","display_name":"DNN-Based Full-Band Speech Synthesis Using GMM Approximation of Spectral Envelope","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3107904486","doi":"https://doi.org/10.1587/transinf.2020edp7075","mag":"3107904486"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2020edp7075","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7075","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020EDP7075/_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/E103.D/12/E103.D_2020EDP7075/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041787266","display_name":"Junya Koguchi","orcid":"https://orcid.org/0009-0007-0682-1546"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Junya KOGUCHI","raw_affiliation_strings":["Meiji University"],"affiliations":[{"raw_affiliation_string":"Meiji University","institution_ids":["https://openalex.org/I16656306"]}]},{"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":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075267422","display_name":"Masanori Morise","orcid":null},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori MORISE","raw_affiliation_strings":["Meiji University"],"affiliations":[{"raw_affiliation_string":"Meiji University","institution_ids":["https://openalex.org/I16656306"]}]},{"author_position":"middle","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":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003450550","display_name":"Shigeki Sagayama","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki SAGAYAMA","raw_affiliation_strings":["The University of Electro-Communications"],"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041787266"],"corresponding_institution_ids":["https://openalex.org/I16656306"],"apc_list":null,"apc_paid":null,"fwci":0.2718,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65822702,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":"E103.D","issue":"12","first_page":"2673","last_page":"2681"},"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":0.9995999932289124,"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":0.9901000261306763,"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/computer-science","display_name":"Computer science","score":0.8034094572067261},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7203277349472046},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6381995677947998},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.5935469269752502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.548933744430542},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5181935429573059},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4935053586959839},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4900623559951782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37926095724105835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3503990173339844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17283794283866882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034094572067261},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7203277349472046},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6381995677947998},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.5935469269752502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.548933744430542},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5181935429573059},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4935053586959839},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4900623559951782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37926095724105835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3503990173339844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17283794283866882},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2020edp7075","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7075","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020EDP7075/_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.2020edp7075","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2020edp7075","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E103.D/12/E103.D_2020EDP7075/_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":[{"display_name":"Peace, Justice and strong institutions","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3291250701","display_name":null,"funder_award_id":"KAKENHI","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"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/G8935930414","display_name":null,"funder_award_id":"19H01116","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3107904486.pdf","grobid_xml":"https://content.openalex.org/works/W3107904486.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W187033940","https://openalex.org/W1523372075","https://openalex.org/W1990505856","https://openalex.org/W2004071961","https://openalex.org/W2009674825","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2156387975","https://openalex.org/W2296704011","https://openalex.org/W2404100688","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2765486990","https://openalex.org/W2921151856","https://openalex.org/W2963609956","https://openalex.org/W2969049672","https://openalex.org/W4251158933","https://openalex.org/W4297952319"],"related_works":["https://openalex.org/W2358051134","https://openalex.org/W1742610407","https://openalex.org/W2912843901","https://openalex.org/W2619026611","https://openalex.org/W2147126679","https://openalex.org/W3171304116","https://openalex.org/W242118163","https://openalex.org/W4287120475","https://openalex.org/W2794438528","https://openalex.org/W2244925781"],"abstract_inverted_index":{"We":[0,127,164],"propose":[1,152,166],"a":[2,40,77,88,153,167],"speech":[3,34,66,114],"analysis-synthesis":[4],"and":[5,56],"deep":[6],"neural":[7],"network":[8],"(DNN)-based":[9],"text-to-speech":[10],"(TTS)":[11],"synthesis":[12,91],"framework":[13,178,188,197],"using":[14,93],"Gaussian":[15,37],"mixture":[16],"model":[17],"(GMM)-based":[18],"approximation":[19,95],"of":[20,39,46,60,84,102,123,133,140,173,195,205],"full-band":[21,113],"spectral":[22,54,142],"envelopes.":[23],"GMMs":[24],"have":[25,73],"excellent":[26,104],"properties":[27],"as":[28,144],"acoustic":[29],"features":[30],"in":[31,100,202,213],"statistic":[32],"parametric":[33],"synthesis.":[35],"Each":[36],"function":[38],"GMM":[41,50,70,125,134,175],"fits":[42],"the":[43,47,52,61,82,124,141,174,192,199,203,210,218,227],"local":[44],"resonance":[45],"spectrum.":[48],"The":[49],"retains":[51],"fine":[53],"envelope":[55],"achieve":[57],"high":[58],"controllability":[59],"structure.":[62],"However,":[63],"since":[64],"conventional":[65,200],"analysis":[67,115],"methods":[68],"(i.e.,":[69],"parameter":[71],"estimation)":[72],"been":[74,98],"formulated":[75,99],"for":[76,112,120,147,155,176],"narrow-band":[78],"speech,":[79],"they":[80],"degrade":[81],"quality":[83,204],"synthetic":[85,181,219,228],"speech.":[86,182,229],"Moreover,":[87],"DNN-based":[89],"TTS":[90],"method":[92,154,194],"GMM-based":[94],"has":[96],"not":[97,129],"spite":[101],"its":[103],"expressive":[105],"ability.":[106],"Therefore,":[107],"we":[108,151],"employ":[109],"peak-picking-based":[110],"initialization":[111,119,193],"to":[116,179],"provide":[117],"better":[118],"iterative":[121],"estimation":[122],"parameters.":[126],"introduce":[128],"only":[130],"prediction":[131],"error":[132,139,212],"parameters":[135],"but":[136],"also":[137,165],"reconstruction":[138,211],"envelopes":[143],"objective":[145],"criteria":[146],"training":[148,215],"DNN.":[149],"Furthermore,":[150],"multi-task":[156],"learning":[157],"based":[158,169],"on":[159,170],"minimizing":[160],"these":[161],"errors":[162],"simultaneously.":[163],"post-filter":[168,224],"variance":[171],"scaling":[172],"our":[177,187,196,222],"enhance":[180],"Experimental":[183],"results":[184],"from":[185],"evaluating":[186],"indicated":[189],"that":[190],"1)":[191],"outperformed":[198],"one":[201],"analysis-synthesized":[206],"speech;":[207,220],"2)":[208],"introducing":[209],"DNN":[214],"significantly":[216],"improved":[217,226],"3)":[221],"variance-scaling-based":[223],"further":[225]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}