{"id":"https://openalex.org/W2786149683","doi":"https://doi.org/10.1109/asru.2017.8269006","title":"Integrated speaker-adaptive speech synthesis","display_name":"Integrated speaker-adaptive speech synthesis","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786149683","doi":"https://doi.org/10.1109/asru.2017.8269006","mag":"2786149683"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8269006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269006","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/74fa3179-7f40-4248-9ca4-cdd05aead071/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037274400","display_name":"Moquan Wan","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":"Moquan Wan","raw_affiliation_strings":["Engineering Department, Cambridge University, UK"],"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028787670","display_name":"Gilles Degottex","orcid":"https://orcid.org/0000-0003-1346-9919"},"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":"Gilles Degottex","raw_affiliation_strings":["Engineering Department, Cambridge University, UK"],"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","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, UK"],"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037274400"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":1.8707,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89654145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"abs 1412 6980","issue":null,"first_page":"705","last_page":"711"},"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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":0.8357205390930176},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7167894840240479},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6852638721466064},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6428194642066956},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5343005061149597},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5266754031181335},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45337599515914917},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.45254018902778625},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4513610005378723},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44717714190483093},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4242698848247528},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40026921033859253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357205390930176},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7167894840240479},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6852638721466064},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6428194642066956},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5343005061149597},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5266754031181335},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45337599515914917},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.45254018902778625},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4513610005378723},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44717714190483093},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4242698848247528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40026921033859253},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru.2017.8269006","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8269006","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/280719","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/280719","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/74fa3179-7f40-4248-9ca4-cdd05aead071/download","source":{"id":"https://openalex.org/S4306401776","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Conference Object"},{"id":"pmh:oai:generic.eprints.org:976522","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/976522/","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":"doi:10.17863/cam.28083","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.28083","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/280719","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/280719","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/74fa3179-7f40-4248-9ca4-cdd05aead071/download","source":{"id":"https://openalex.org/S4306401776","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":"Conference Object"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2786149683.pdf","grobid_xml":"https://content.openalex.org/works/W2786149683.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W344150399","https://openalex.org/W1165382972","https://openalex.org/W1522301498","https://openalex.org/W1539053441","https://openalex.org/W2028235769","https://openalex.org/W2046056978","https://openalex.org/W2049686551","https://openalex.org/W2094721231","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2152175008","https://openalex.org/W2292984643","https://openalex.org/W2395750323","https://openalex.org/W2399762392","https://openalex.org/W2403307129","https://openalex.org/W2516321201","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2605320104","https://openalex.org/W2759925408","https://openalex.org/W2901997113","https://openalex.org/W2964121744","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2099333848"],"abstract_inverted_index":{"Enabling":[0],"speech":[1,137],"synthesis":[2,73,105,125,185,202],"systems":[3],"to":[4,7,40,68,88,157],"rapidly":[5],"adapt":[6],"sound":[8],"like":[9],"a":[10,32,149,218],"particular":[11],"speaker":[12,54,95,100,135,193],"is":[13,26,37,87,148,155,196,206],"an":[14,90,130,143,191],"essential":[15],"attribute":[16],"for":[17,93,103,118,134,198],"building":[18],"personalised":[19],"systems.":[20],"For":[21,139],"deep-learning":[22],"based":[23,145],"approaches,":[24],"this":[25,52],"difficult":[27],"as":[28,168,170,183],"these":[29],"networks":[30],"use":[31,199],"highly":[33],"distributed":[34],"representation.":[35],"It":[36],"not":[38],"simple":[39],"interpret":[41],"the":[42,47,69,72,76,79,82,99,104,116,119,124,140,152,159,162,173,180,184,201,209,227],"model":[43],"parameters,":[44],"which":[45,65,147],"complicates":[46],"adaptation":[48],"process.":[49],"To":[50],"address":[51],"problem,":[53],"characteristics":[55],"can":[56],"be":[57],"encapsulated":[58],"in":[59],"fixed-length":[60],"speaker-specific":[61],"Identity":[62],"Vectors":[63],"(iVectors),":[64],"are":[66,177],"appended":[67],"input":[70],"of":[71,81,115,151,172],"network.":[74,126],"Altering":[75],"iVector":[77,92,141],"changes":[78],"nature":[80,171],"synthesised":[83],"speech.":[84],"The":[85,107,204,213],"challenge":[86],"derive":[89],"optimal":[91,197],"each":[94],"that":[96,195],"encodes":[97],"all":[98],"attributes":[101],"required":[102],"system.":[106,203],"standard":[108,228],"approach":[109],"involves":[110],"two":[111],"separate":[112],"stages:":[113],"estimation":[114],"iVectors":[117],"training":[120,123,132],"data;":[121],"and":[122,222],"This":[127,165,188],"paper":[128],"proposes":[129],"integrated":[131],"scheme":[133],"adaptive":[136],"synthesis.":[138],"extraction,":[142],"attention":[144,166,220],"mechanism,":[146,167],"function":[150],"context":[153],"labels,":[154],"used":[156],"combine":[158],"data":[160],"from":[161,226],"target":[163],"speaker.":[164],"well":[169],"features":[174],"being":[175],"merged,":[176],"optimised":[178],"at":[179],"same":[181],"time":[182],"network":[186],"parameters.":[187],"should":[189],"yield":[190],"iVector-like":[192],"representation":[194],"with":[200],"system":[205,215],"evaluated":[207],"on":[208],"Voice":[210],"Bank":[211],"corpus.":[212],"resulting":[214],"automatically":[216],"provides":[217],"sensible":[219],"sequence":[221],"shows":[223],"improved":[224],"performance":[225],"approach.":[229]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
