{"id":"https://openalex.org/W2889226978","doi":"https://doi.org/10.21437/interspeech.2018-1154","title":"Waveform-Based Speaker Representations for Speech Synthesis","display_name":"Waveform-Based Speaker Representations for Speech Synthesis","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2889226978","doi":"https://doi.org/10.21437/interspeech.2018-1154","mag":"2889226978"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1154","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.17863/cam.30289","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":["Cambridge University Engineering Department, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, 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":["Cambridge University Engineering Department, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, 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":["Cambridge University Engineering Department, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, 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":0.3385,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68828881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"897","last_page":"901"},"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":0.9947999715805054,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.994700014591217,"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/computer-science","display_name":"Computer science","score":0.8273507356643677},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7270841002464294},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6813138127326965},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.676354169845581},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6539019346237183},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5573642253875732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.485624223947525},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4663248360157013},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4506740868091583},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44581368565559387},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42396336793899536},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4108070731163025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3210917115211487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8273507356643677},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7270841002464294},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6813138127326965},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.676354169845581},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6539019346237183},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5573642253875732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.485624223947525},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4663248360157013},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4506740868091583},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44581368565559387},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42396336793899536},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4108070731163025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3210917115211487},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2018-1154","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:1011857","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1011857/","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:www.repository.cam.ac.uk:1810/282926","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/282926","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","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":"doi:10.17863/cam.30289","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.30289","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":"doi:10.17863/cam.30289","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.30289","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W344150399","https://openalex.org/W1522301498","https://openalex.org/W1539053441","https://openalex.org/W2046056978","https://openalex.org/W2094721231","https://openalex.org/W2107789863","https://openalex.org/W2121812409","https://openalex.org/W2150769028","https://openalex.org/W2194775991","https://openalex.org/W2292984643","https://openalex.org/W2395750323","https://openalex.org/W2403307129","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2763767706","https://openalex.org/W2786149683","https://openalex.org/W2901997113","https://openalex.org/W2949382160","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"Speaker":[0],"adaptation":[1,32],"is":[2,43,80,104,123,164,168,177],"a":[3,8,46,84,96,129,152],"key":[4],"aspect":[5],"of":[6,10,98,113,159],"building":[7,151],"range":[9,97],"speech":[11,17,131],"processing":[12],"systems,":[13],"for":[14,95,109,150],"example":[15,172],"personalised":[16],"synthesis.":[18],"For":[19],"deep-learning":[20],"based":[21],"approaches,":[22],"the":[23,61,73,77,89,101,110,116,120,136,161,171],"model":[24,74],"parameters":[25],"are":[26,125],"hard":[27],"to":[28,39,44,60,68,92,106],"interpret,":[29],"making":[30,157],"speaker":[31,51,78,121,155,175],"more":[33],"challenging.":[34],"One":[35],"widely":[36],"used":[37,94,169],"method":[38],"address":[40],"this":[41,55,144,194],"problem":[42],"extract":[45],"fixed":[47],"length":[48],"vector":[49],"as":[50,56,170],"representation,":[52,156],"and":[53,192],"use":[54,158],"an":[57,146,186],"additional":[58],"input":[59],"task-specific":[62],"model.":[63],"This":[64,87,133,189],"allows":[65,88],"speaker-specific":[66],"output":[67],"be":[69,93,107,141],"generated,":[70],"without":[71],"modifying":[72],"parameters.":[75],"However,":[76],"representation":[79,103,122,176],"often":[81,128],"extracted":[82,102,124],"in":[83],"task-independent":[85,198],"fashion.":[86],"same":[90],"approach":[91],"tasks,":[99],"but":[100],"unlikely":[105],"optimal":[108],"specific":[111,154],"task":[112,153],"interest.":[114],"Furthermore,":[115],"features":[117],"from":[118,179],"which":[119],"usually":[126],"pre-defined,":[127],"standard":[130,197],"representation.":[132],"may":[134],"limit":[135],"available":[137,162],"information":[138,184],"that":[139],"can":[140],"used.":[142],"In":[143],"paper,":[145],"integrated":[147],"optimisation":[148],"framework":[149,195],"all":[160],"information,":[163],"proposed.":[165],"Speech":[166],"synthesis":[167],"task.":[173],"The":[174],"derived":[178],"raw":[180],"waveform,":[181],"incorporating":[182],"text":[183],"via":[185],"attention":[187],"mechanism.":[188],"paper":[190],"evaluates":[191],"compares":[193],"with":[196],"forms.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}