{"id":"https://openalex.org/W1966136862","doi":"https://doi.org/10.1109/icassp.2014.6853603","title":"Multiple-average-voice-based speech synthesis","display_name":"Multiple-average-voice-based speech synthesis","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1966136862","doi":"https://doi.org/10.1109/icassp.2014.6853603","mag":"1966136862"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":["Engineering Department, Cambridge University, Cambridge, UK","Engineering Department, Cambridge University, Cambridge, UK,"],"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK,","institution_ids":["https://openalex.org/I241749"]}]},{"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":["Engineering Department, Cambridge University, Cambridge, UK","Engineering Department, Cambridge University, Cambridge, UK,"],"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, 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, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, 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, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003588321"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":1.6881,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86958054,"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":"285","last_page":"289"},"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":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9925000071525574,"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/naturalness","display_name":"Naturalness","score":0.8391771912574768},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7587363719940186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.689967155456543},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6526237726211548},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6168736219406128},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5943390130996704},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5799894332885742},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4541669487953186},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4200918674468994},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.417539119720459},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13405048847198486},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08372512459754944},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06345123052597046}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8391771912574768},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587363719940186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.689967155456543},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6526237726211548},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6168736219406128},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5943390130996704},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5799894332885742},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4541669487953186},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4200918674468994},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.417539119720459},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13405048847198486},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08372512459754944},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06345123052597046},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6853603","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:647275","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/647275/","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":"Article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/11244053-5001-4715-bd73-c8a7022dbf77","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/11244053-5001-4715-bd73-c8a7022dbf77","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W57368184","https://openalex.org/W68089216","https://openalex.org/W80543058","https://openalex.org/W102093577","https://openalex.org/W126988493","https://openalex.org/W167766911","https://openalex.org/W344150399","https://openalex.org/W1547848553","https://openalex.org/W1605997703","https://openalex.org/W1861150963","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2025638820","https://openalex.org/W2039800941","https://openalex.org/W2042691334","https://openalex.org/W2069631319","https://openalex.org/W2093450784","https://openalex.org/W2095437083","https://openalex.org/W2106792148","https://openalex.org/W2122272452","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2150906086","https://openalex.org/W2153914468","https://openalex.org/W2165143604","https://openalex.org/W2228674556","https://openalex.org/W2269105564","https://openalex.org/W6603264027","https://openalex.org/W6611766843"],"related_works":["https://openalex.org/W2007171027","https://openalex.org/W2395237272","https://openalex.org/W1492383498","https://openalex.org/W3015826515","https://openalex.org/W2159219421","https://openalex.org/W2082426107","https://openalex.org/W2992420079","https://openalex.org/W3000622584","https://openalex.org/W2964169091","https://openalex.org/W2791474202"],"abstract_inverted_index":{"This":[0,51],"paper":[1],"describes":[2],"a":[3,21,66,80,84,144,168],"novel":[4],"approach":[5,79],"for":[6,48,135],"the":[7,18,33,40,43,53,74,77,98,110,116,123,130,154,175],"speaker":[8,49,62,132,141,177],"adaptation":[9,142],"of":[10,20,23,35,55,82,91,146,156,159],"statistical":[11],"parametric":[12],"speech":[13,158],"synthesis":[14],"systems":[15],"based":[16],"on":[17,39,59,88,143],"interpolation":[19],"set":[22,81],"average":[24,44],"voice":[25,45],"models":[26],"(AVM).":[27],"Recent":[28],"results":[29],"have":[30],"shown":[31],"that":[32,153],"quality/naturalness":[34,155],"adapted":[36,114,120,133,160],"voices":[37,161],"depends":[38],"distance":[41],"from":[42,64,109,122],"model":[46],"used":[47],"adaptation.":[50,75],"suggests":[52],"use":[54],"several":[56],"AVMs":[57,124],"trained":[58,87],"carefully":[60],"chosen":[61],"clusters":[63,90],"which":[65,93],"more":[67],"suitable":[68],"AVM":[69,108,171],"can":[70],"be":[71],"selected/interpolated":[72],"during":[73,97],"In":[76],"proposed":[78],"AVMs,":[83],"multiple-AVM,":[85],"is":[86,112,138,162],"distinct":[89],"speakers":[92,148],"are":[94,125],"iteratively":[95],"re-assigned":[96],"estimation":[99],"process":[100],"initialised":[101],"according":[102,173],"to":[103,128,174],"metadata.":[104],"During":[105],"adaptation,":[106],"each":[107],"multiple-AVM":[111],"first":[113],"towards":[115],"target":[117,176],"speaker.":[118],"The":[119],"means":[121],"then":[126],"interpolated":[127],"yield":[129],"final":[131],"mean":[134],"synthesis.":[136],"It":[137],"shown,":[139],"performing":[140],"corpus":[145],"British":[147],"with":[149],"various":[150],"regional":[151],"accents,":[152],"synthetic":[157],"significantly":[163],"higher":[164],"than":[165],"when":[166],"considering":[167],"single":[169],"factor-independent":[170],"selected":[172],"characteristics.":[178]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}