{"id":"https://openalex.org/W3048869804","doi":"https://doi.org/10.21437/interspeech.2020-2793","title":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion","display_name":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3048869804","doi":"https://doi.org/10.21437/interspeech.2020-2793","mag":"3048869804"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2793","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.05809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041343074","display_name":"Dipjyoti Paul","orcid":"https://orcid.org/0000-0002-5320-1602"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dipjyoti Paul","raw_affiliation_strings":["University of Crete"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Crete","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020314306","display_name":"Muhammed P.V. Shifas","orcid":"https://orcid.org/0000-0002-2449-8507"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Muhammed P.V. Shifas","raw_affiliation_strings":["University of Crete"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Crete","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010084334","display_name":"Yannis Pantazis","orcid":"https://orcid.org/0000-0002-2009-7562"},"institutions":[{"id":"https://openalex.org/I142617266","display_name":"University of Crete","ror":"https://ror.org/00dr28g20","country_code":"GR","type":"education","lineage":["https://openalex.org/I142617266"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Pantazis","raw_affiliation_strings":["University of Crete"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Crete","institution_ids":["https://openalex.org/I142617266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I8901234","display_name":"Foundation for Research and Technology Hellas","ror":"https://ror.org/052rphn09","country_code":"GR","type":"facility","lineage":["https://openalex.org/I8901234"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Foundation For Research And Technology-Hellas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Foundation For Research And Technology-Hellas","institution_ids":["https://openalex.org/I8901234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5416,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7371109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1361","last_page":"1365"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9955999851226807,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.9091023206710815},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6497305631637573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6393907070159912},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6327530145645142}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.9091023206710815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6497305631637573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6393907070159912},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6327530145645142},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2020-2793","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2793","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.05809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05809","pdf_url":"https://arxiv.org/pdf/2008.05809","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3048869804","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2008.05809.pdf","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:zenodo.org:4249325","is_oa":true,"landing_page_url":"https://zenodo.org/record/4249325","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2008.05809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.05809","pdf_url":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.05809","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.05809","pdf_url":"https://arxiv.org/pdf/2008.05809","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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W197380572","https://openalex.org/W1519339192","https://openalex.org/W1716865208","https://openalex.org/W1970405784","https://openalex.org/W2072328708","https://openalex.org/W2104387086","https://openalex.org/W2118258949","https://openalex.org/W2129387557","https://openalex.org/W2139913386","https://openalex.org/W2149948223","https://openalex.org/W2163010125","https://openalex.org/W2165698076","https://openalex.org/W2171878011","https://openalex.org/W2399475675","https://openalex.org/W2404548911","https://openalex.org/W2636064478","https://openalex.org/W2750452568","https://openalex.org/W2911412811","https://openalex.org/W2936173958","https://openalex.org/W2938932039","https://openalex.org/W2963609956","https://openalex.org/W2963782041","https://openalex.org/W2964307104","https://openalex.org/W2972497784","https://openalex.org/W2972772214","https://openalex.org/W3048423403"],"related_works":["https://openalex.org/W3097587372","https://openalex.org/W763017202","https://openalex.org/W1716865208","https://openalex.org/W2005709450","https://openalex.org/W3138243152","https://openalex.org/W2051593625","https://openalex.org/W1519339192","https://openalex.org/W3148935696","https://openalex.org/W2395675680","https://openalex.org/W2903592149","https://openalex.org/W2574278440","https://openalex.org/W1572444327","https://openalex.org/W1970405784","https://openalex.org/W2602037738","https://openalex.org/W2986082996","https://openalex.org/W3035123403","https://openalex.org/W65497148","https://openalex.org/W2163010125","https://openalex.org/W1731717999","https://openalex.org/W2066754815"],"abstract_inverted_index":{"The":[0,73],"increased":[1],"adoption":[2],"of":[3,14,27,35,180],"digital":[4],"assistants":[5],"makes":[6],"text-to-speech":[7],"(TTS)":[8],"synthesis":[9],"systems":[10],"an":[11],"indispensable":[12],"feature":[13],"modern":[15],"mobile":[16],"devices.":[17],"It":[18],"is":[19],"hence":[20],"desirable":[21],"to":[22,52,99,115,154,194],"build":[23],"a":[24,61],"system":[25,76,139],"capable":[26],"generating":[28],"highly":[29],"intelligible":[30],"speech":[31,75,175],"in":[32,43,129,148,156,188],"the":[33,106,110,127,135,161,174,195],"presence":[34],"noise.":[36],"Past":[37],"studies":[38],"have":[39],"investigated":[40],"style":[41,84],"conversion":[42],"TTS":[44,71,120,138,163,171,197],"synthesis,":[45],"yet":[46],"degraded":[47],"synthesized":[48],"quality":[49],"often":[50],"leads":[51],"worse":[53],"intelligibility.":[54],"To":[55],"overcome":[56],"such":[57],"limitations,":[58],"we":[59],"proposed":[60,74,136],"novel":[62],"transfer":[63],"learning":[64],"approach":[65],"using":[66],"Tacotron":[67],"and":[68,86,90,146,152,184],"WaveRNN":[69],"based":[70],"synthesis.":[72],"exploits":[77],"two":[78],"modification":[79],"strategies:":[80],"(a)":[81],"Lombard":[82],"speaking":[83],"data":[85],"(b)":[87],"Spectral":[88],"Shaping":[89],"Dynamic":[91],"Range":[92],"Compression":[93],"(SSDRC)":[94],"which":[95],"has":[96],"been":[97],"shown":[98],"provide":[100],"high":[101],"intelligibility":[102,176],"gains":[103],"by":[104,126],"redistributing":[105],"signal":[107],"energy":[108],"on":[109],"time-frequency":[111],"domain.":[112],"We":[113],"refer":[114],"this":[116],"extension":[117],"as":[118,124],"Lombard-SSDRC":[119,137,170],"system.":[121],"Intelligibility":[122,128],"enhancement":[123],"quantified":[125],"Bits":[130],"(SIIB-Gauss)":[131],"measure":[132],"shows":[133,140,168],"that":[134,169],"significant":[141],"relative":[142,178],"improvement":[143,179],"between":[144],"110%":[145],"130%":[147],"speech-shaped":[149],"noise":[150,158],"(SSN),":[151],"47%":[153],"140%":[155],"competing-speaker":[157],"(CSN)":[159],"against":[160],"state-of-the-art":[162],"approach.":[164],"Additional":[165],"subjective":[166],"evaluation":[167],"successfully":[172],"increases":[173],"with":[177],"455%":[181],"for":[182,186],"SSN":[183],"104%":[185],"CSN":[187],"median":[189],"keyword":[190],"correction":[191],"rate":[192],"compared":[193],"baseline":[196],"method.":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}