{"id":"https://openalex.org/W3097264669","doi":"https://doi.org/10.21437/interspeech.2020-2116","title":"Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder","display_name":"Neural Text-to-Speech with a Modeling-by-Generation Excitation Vocoder","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3097264669","doi":"https://doi.org/10.21437/interspeech.2020-2116","mag":"3097264669"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2116","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.00132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104035145","display_name":"Eunwoo Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eunwoo Song","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055817509","display_name":"Min-Jae Hwang","orcid":"https://orcid.org/0000-0002-7376-009X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min-Jae Hwang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669485","display_name":"Ryuichi Yamamoto","orcid":"https://orcid.org/0000-0003-0299-5470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuichi Yamamoto","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033037115","display_name":"Jinseob Kim","orcid":"https://orcid.org/0000-0002-9403-605X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin-Seob Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101576669","display_name":"Ohsung Kwon","orcid":"https://orcid.org/0000-0003-3880-0911"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ohsung Kwon","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101480212","display_name":"Jae-Min Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jae-Min Kim","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.554,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.438836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":84},"biblio":{"volume":null,"issue":null,"first_page":"3570","last_page":"3574"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998,"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":0.998,"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":0.9849,"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/T12031","display_name":"Speech and dialogue systems","score":0.9688,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.5782761},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5175528},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.46524298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82401633},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7491566},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6852684},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.64496374},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5782761},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5175528},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.50065184},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.46524298},{"id":"https://openalex.org/C83581075","wikidata":"https://www.wikidata.org/wiki/Q1361503","display_name":"Excitation","level":2,"score":0.4361764},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43291634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36299372},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.35794967},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08473459},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08057821},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2116","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2008.00132","pdf_url":"https://arxiv.org/pdf/2008.00132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2008.00132","pdf_url":"https://arxiv.org/pdf/2008.00132","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4300049944","https://openalex.org/W4200068392","https://openalex.org/W3164858600","https://openalex.org/W3109498233","https://openalex.org/W2147126679","https://openalex.org/W2115039802","https://openalex.org/W2039489009","https://openalex.org/W2031768607","https://openalex.org/W2020989338","https://openalex.org/W1823617068"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9,26,31,43,56,187],"modeling-by-generation":[4],"(MbG)":[5],"excitation":[6,17,34,113],"vocoder":[7,65,90,127],"for":[8,143],"neural":[10,16,126],"text-to-speech":[11],"(TTS)":[12],"system.":[13],"Recently":[14],"proposed":[15,110,179],"vocoders":[18,39],"can":[19,169],"realize":[20],"qualified":[21],"waveform":[22],"generation":[23],"by":[24,117,185],"combining":[25],"vocal":[27],"tract":[28],"filter":[29],"with":[30],"WaveNet-based":[32],"glottal":[33],"generator.":[35],"However,":[36],"when":[37],"these":[38],"are":[40,81,158],"used":[41],"in":[42,160],"TTS":[44,195],"system,":[45],"the":[46,64,78,85,89,104,109,112,118,125,135,144,149,154,161,178,194],"quality":[47],"of":[48,77,88,191],"synthesized":[49],"speech":[50,184],"is":[51,66,115,128],"often":[52],"degraded":[53],"owing":[54],"to":[55,98,133,141],"mismatch":[57,167],"between":[58],"training":[59,106,162],"and":[60,124,163],"synthesis":[61,86,164],"steps.":[62],"Specifically,":[63],"separately":[67],"trained":[68],"from":[69,148],"an":[70,100],"acoustic":[71,79,119,150],"model":[72,80],"front-end.":[73],"Therefore,":[74],"estimation":[75,145],"errors":[76,146],"inevitably":[82],"boosted":[83],"throughout":[84],"process":[87],"back-end.":[91],"To":[92],"address":[93],"this":[94],"problem,":[95],"we":[96],"propose":[97],"incorporate":[99],"MbG":[101],"structure":[102],"into":[103],"vocoder's":[105],"process.":[107],"In":[108],"method,":[111],"signal":[114],"extracted":[116],"model's":[120],"generated":[121,155],"spectral":[122,156],"parameters,":[123],"then":[129],"optimized":[130],"not":[131],"only":[132],"learn":[134],"target":[136],"excitation's":[137],"distribution":[138],"but":[139],"also":[140],"compensate":[142],"occurring":[147],"model.":[151],"Furthermore,":[152],"as":[153],"parameters":[157],"shared":[159],"steps,":[165],"their":[166],"conditions":[168],"be":[170],"reduced":[171],"effectively.":[172],"The":[173],"experimental":[174],"results":[175],"verify":[176],"that":[177],"system":[180],"provides":[181],"high-quality":[182],"synthetic":[183],"achieving":[186],"mean":[188],"opinion":[189],"score":[190],"4.57":[192],"within":[193],"framework.":[196]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3097264669","counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4}],"updated_date":"2025-01-12T12:55:39.349789","created_date":"2020-11-09"}