{"id":"https://openalex.org/W2177575896","doi":"https://doi.org/10.21437/interspeech.2015-131","title":"Reconstructing voices within the multiple-average-voice-model framework","display_name":"Reconstructing voices within the multiple-average-voice-model framework","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2177575896","doi":"https://doi.org/10.21437/interspeech.2015-131","mag":"2177575896"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-131","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/20118459/IS2015_corrected.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003588321","display_name":"Pierre Lanchantin","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pierre Lanchantin","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge CB2 1PZ, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge CB2 1PZ, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038279043","display_name":"Christophe Veaux","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Christophe Veaux","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge CB2 1PZ, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge CB2 1PZ, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003588321"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.8897,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83161148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2232","last_page":"2236"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.996999979019165,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7482326626777649},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7102264761924744},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.706238865852356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7011856436729431},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5892683863639832},{"id":"https://openalex.org/keywords/voice-analysis","display_name":"Voice analysis","score":0.5505219101905823},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5018362998962402},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49479931592941284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28410443663597107},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.11485546827316284},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08311766386032104},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0785720944404602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482326626777649},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7102264761924744},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.706238865852356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7011856436729431},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5892683863639832},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.5505219101905823},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5018362998962402},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49479931592941284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28410443663597107},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.11485546827316284},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08311766386032104},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0785720944404602},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-131","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/2425651f-f140-4da1-9cf0-4ad50690d377","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/2425651f-f140-4da1-9cf0-4ad50690d377","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20118459/IS2015_corrected.pdf","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":""},{"id":"pmh:oai:generic.eprints.org:755743","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/755743/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/2425651f-f140-4da1-9cf0-4ad50690d377","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/2425651f-f140-4da1-9cf0-4ad50690d377","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":"Lanchantin, P, Veaux, C, Gales, M J F, King, S & Yamagishi, J 2015, Reconstructing Voices within the Multiple-Average-Voice-Model framework. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 2232-2236, Interspeech 2015, Dresden, Germany, 6/09/15. < http://www.isca-speech.org/archive/interspeech_2015/i15_2232.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/2425651f-f140-4da1-9cf0-4ad50690d377","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/2425651f-f140-4da1-9cf0-4ad50690d377","pdf_url":"https://www.pure.ed.ac.uk/ws/files/20118459/IS2015_corrected.pdf","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":""},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2177575896.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W126988493","https://openalex.org/W333180468","https://openalex.org/W344150399","https://openalex.org/W1576115189","https://openalex.org/W1966136862","https://openalex.org/W2002342963","https://openalex.org/W2025638820","https://openalex.org/W2042691334","https://openalex.org/W2053741679","https://openalex.org/W2056258844","https://openalex.org/W2069631319","https://openalex.org/W2093450784","https://openalex.org/W2100407194","https://openalex.org/W2106792148","https://openalex.org/W2109848220","https://openalex.org/W2122272452","https://openalex.org/W2129142580","https://openalex.org/W2147305094","https://openalex.org/W2153914468","https://openalex.org/W2250668798","https://openalex.org/W2269105564","https://openalex.org/W2396988173"],"related_works":["https://openalex.org/W1992908141","https://openalex.org/W1973693762","https://openalex.org/W25843091","https://openalex.org/W3144640894","https://openalex.org/W4399374970","https://openalex.org/W2072764920","https://openalex.org/W1621367523","https://openalex.org/W2854103257","https://openalex.org/W2512149115","https://openalex.org/W241284251"],"abstract_inverted_index":{"Personalisation":[0],"of":[1,13,26,35,57,80,83,86,115,133,146,180],"voice":[2,40,137,161],"output":[3],"communication":[4],"AIDS":[5],"(VOCAs)":[6],"allows":[7],"to":[8,43,122],"preserve":[9],"the":[10,24,39,50,55,58,62,84,87,90,112,123,131,159,169,181],"vocal":[11],"identity":[12,85],"people":[14],"suffering":[15],"from":[16,74],"speech":[17,28,63,156],"disorders.":[18],"This":[19,65],"can":[20,66,119,150,162],"be":[21,67,120,151,163],"achieved":[22],"by":[23,53,69,111,166],"adaptation":[25,36,147],"HMM-based":[27],"synthesis":[29],"systems":[30],"using":[31],"a":[32,75,107,142,154,177],"small":[33,144],"amount":[34,145],"data.":[37],"When":[38],"has":[41,95],"begun":[42],"deteriorate,":[44],"reconstruction":[45],"is":[46,102],"still":[47],"possible":[48],"in":[49,153],"statistical":[51],"domain":[52],"correcting":[54],"parameters":[56,73],"models":[59],"associated":[60],"with":[61,72,176],"disorder.":[64],"done":[68],"substituting":[70],"those":[71],"donor's":[76],"voice,":[77],"at":[78],"risk":[79],"losing":[81],"part":[82],"patient.":[88],"Recently,":[89],"Multiple-Average-Voice-Model":[91],"(Multiple":[92],"AVM)":[93],"framework":[94,135],"been":[96],"proposed":[97],"for":[98,136],"speaker":[99,108],"adaptation.":[100],"Adaptation":[101],"performed":[103,152],"via":[104],"interpolation":[105,149,170],"into":[106],"eigenspace":[109,157],"spanned":[110],"mean":[113],"vectors":[114],"speaker-adapted":[116],"AVMs":[117],"which":[118],"tuned":[121],"individual":[124],"speaker.":[125],"In":[126],"this":[127,134],"paper,":[128],"we":[129],"present":[130],"benefits":[132],"reconstruction:":[138],"it":[139],"requires":[140],"only":[141],"very":[143],"data,":[148],"clean":[155],"and":[158],"resulting":[160],"easily":[164],"fine-tuned":[165],"acting":[167],"on":[168],"weights.":[171],"We":[172],"illustrate":[173],"our":[174],"points":[175],"subjective":[178],"assessment":[179],"reconstructed":[182],"voice.":[183]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}