{"id":"https://openalex.org/W3116685286","doi":"https://doi.org/10.23919/eusipco47968.2020.9287684","title":"Flexible parametric implantation of voicing in whispered speech under scarce training data","display_name":"Flexible parametric implantation of voicing in whispered speech under scarce training data","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3116685286","doi":"https://doi.org/10.23919/eusipco47968.2020.9287684","mag":"3116685286"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287684","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401343","display_name":"Jo\u00e3o Silva","orcid":"https://orcid.org/0000-0002-2460-8825"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Joao Silva","raw_affiliation_strings":["University of Porto-FEUP-DEEC, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto-FEUP-DEEC, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026987730","display_name":"Marco Oliveira","orcid":"https://orcid.org/0000-0002-3161-1109"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Marco Oliveira","raw_affiliation_strings":["University of Porto-FEUP-DEEC, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto-FEUP-DEEC, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069607429","display_name":"A\u0144\u0131bal Ferreira","orcid":"https://orcid.org/0000-0002-7278-6749"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Anibal Ferreira","raw_affiliation_strings":["University of Porto-FEUP-DEEC, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Porto-FEUP-DEEC, Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4062,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71268908,"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":"416","last_page":"420"},"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":0.9995999932289124,"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":0.9927999973297119,"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":0.7861316204071045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7115422487258911},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6251227855682373},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6044292449951172},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.5173994302749634},{"id":"https://openalex.org/keywords/morphing","display_name":"Morphing","score":0.5113191604614258},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.4323379099369049},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.42982035875320435},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.42832237482070923},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.4155210554599762},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41101229190826416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2779870629310608},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0979929268360138},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09459152817726135}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861316204071045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7115422487258911},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6251227855682373},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6044292449951172},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5173994302749634},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.5113191604614258},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.4323379099369049},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.42982035875320435},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.42832237482070923},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.4155210554599762},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41101229190826416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2779870629310608},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0979929268360138},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09459152817726135},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287684","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W26933160","https://openalex.org/W95551363","https://openalex.org/W1187407439","https://openalex.org/W1560013842","https://openalex.org/W1561747916","https://openalex.org/W1901696025","https://openalex.org/W2029027380","https://openalex.org/W2033493106","https://openalex.org/W2056852181","https://openalex.org/W2085849982","https://openalex.org/W2116756305","https://openalex.org/W2119648481","https://openalex.org/W2141181014","https://openalex.org/W2153541119","https://openalex.org/W2154291215","https://openalex.org/W2473289087","https://openalex.org/W2607377433","https://openalex.org/W2799712304","https://openalex.org/W2889417860","https://openalex.org/W2896501492","https://openalex.org/W2913006054","https://openalex.org/W3015598639","https://openalex.org/W3109938142","https://openalex.org/W6603921752","https://openalex.org/W6633680552","https://openalex.org/W6755353286"],"related_works":["https://openalex.org/W1679315481","https://openalex.org/W3151495635","https://openalex.org/W2036753972","https://openalex.org/W4385170164","https://openalex.org/W4236870338","https://openalex.org/W2016917053","https://openalex.org/W1580681114","https://openalex.org/W1996861825","https://openalex.org/W51472912","https://openalex.org/W4362722828"],"abstract_inverted_index":{"Whispered-voice":[0],"to":[1,98,112],"normal-voice":[2],"conversion":[3,14],"is":[4],"typically":[5],"achieved":[6],"using":[7,12,22],"codec-based":[8],"analysis":[9],"and":[10,18,45,64,81,94,109,120,130],"re-synthesis,":[11],"statistical":[13,40],"of":[15,36,47,58,90],"important":[16],"spectral":[17,124],"prosodic":[19],"features,":[20],"or":[21,42],"data-driven":[23],"end-to-end":[24],"signal":[25,118],"conversion.":[26],"These":[27],"approaches":[28],"are":[29,96],"however":[30],"highly":[31],"constrained":[32],"by":[33],"the":[34,37,39,43,48],"architecture":[35],"codec,":[38],"projection,":[41],"size":[44],"quality":[46],"training":[49],"data.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,65],"presume":[55],"direct":[56],"implantation":[57],"voiced":[59,84],"phonemes":[60],"in":[61,116,137],"whispered":[62],"speech":[63],"focus":[66],"on":[67],"fully":[68],"flexible":[69],"parametric":[70],"models":[71],"that":[72],"i)":[73],"can":[74,133],"be":[75,134],"independently":[76,135],"controlled,":[77],"ii)":[78],"synthesize":[79],"natural":[80,107],"linguistically":[82],"correct":[83],"phonemes,":[85],"iii)":[86],"preserve":[87],"idiosyncratic":[88],"characteristics":[89],"a":[91,117],"given":[92],"speaker,":[93],"iv)":[95],"amenable":[97],"co-articulation":[99],"effects":[100],"through":[101],"simple":[102],"model":[103],"interpolation.":[104],"We":[105],"use":[106],"spoken":[108],"sung":[110],"vowels":[111],"illustrate":[113],"these":[114],"capabilities":[115],"modeling":[119],"re-synthesis":[121],"process":[122],"where":[123],"magnitude,":[125],"phase":[126],"structure,":[127],"F0":[128],"contour":[129],"sound":[131],"morphing":[132],"controlled":[136],"arbitrary":[138],"ways.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}