{"id":"https://openalex.org/W1971670143","doi":"https://doi.org/10.1109/taslp.2014.2385478","title":"Speaker and Expression Factorization for Audiobook Data: Expressiveness and Transplantation","display_name":"Speaker and Expression Factorization for Audiobook Data: Expressiveness and Transplantation","publication_year":2014,"publication_date":"2014-12-23","ids":{"openalex":"https://openalex.org/W1971670143","doi":"https://doi.org/10.1109/taslp.2014.2385478","mag":"1971670143"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2385478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2385478","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.repository.cam.ac.uk/bitstreams/e5a69bbc-160b-471f-ae7b-920cc90589f3/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070433127","display_name":"Langzhou Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Langzhou Chen","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Lab, Cambridge, U.K","Cambridge Research Lab, Toshiba Research Europe Limited, Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Lab, Cambridge, U.K","institution_ids":[]},{"raw_affiliation_string":"Cambridge Research Lab, Toshiba Research Europe Limited, Cambridge, U.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075928867","display_name":"Norbert Braunschweiler","orcid":"https://orcid.org/0000-0003-1388-440X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norbert Braunschweiler","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Lab, Cambridge, U.K","Cambridge Research Lab, Toshiba Research Europe Limited, Cambridge, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Lab, Cambridge, U.K","institution_ids":[]},{"raw_affiliation_string":"Cambridge Research Lab, Toshiba Research Europe Limited, Cambridge, U.K","institution_ids":[]}]},{"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, Cambridge, U.K","Engineering Department, Cambridge University, Cambridge, U.K.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Engineering Department, Cambridge University, Cambridge, U.K.#TAB#","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070433127"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6915,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.8702207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"23","issue":"4","first_page":"605","last_page":"618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9900000095367432,"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":0.9884999990463257,"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":0.741223931312561},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.644537627696991},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5270079374313354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5015387535095215},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.4592779278755188},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.43574652075767517},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.42593657970428467},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3484307527542114},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10400918126106262},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08437436819076538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741223931312561},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.644537627696991},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5270079374313354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5015387535095215},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4592779278755188},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43574652075767517},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.42593657970428467},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3484307527542114},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10400918126106262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08437436819076538},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2014.2385478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2385478","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/247404","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/247404","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/e5a69bbc-160b-471f-ae7b-920cc90589f3/download","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:generic.eprints.org:677604","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/677604/","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"}],"best_oa_location":{"id":"pmh:oai:www.repository.cam.ac.uk:1810/247404","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/247404","pdf_url":"https://www.repository.cam.ac.uk/bitstreams/e5a69bbc-160b-471f-ae7b-920cc90589f3/download","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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1971670143.pdf","grobid_xml":"https://content.openalex.org/works/W1971670143.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W80543058","https://openalex.org/W126988493","https://openalex.org/W573259127","https://openalex.org/W1517939602","https://openalex.org/W1966874939","https://openalex.org/W1976637928","https://openalex.org/W2009417200","https://openalex.org/W2025638820","https://openalex.org/W2075669045","https://openalex.org/W2079521622","https://openalex.org/W2085013480","https://openalex.org/W2087110403","https://openalex.org/W2091430793","https://openalex.org/W2095437083","https://openalex.org/W2105468141","https://openalex.org/W2117274752","https://openalex.org/W2119929864","https://openalex.org/W2125552374","https://openalex.org/W2126672039","https://openalex.org/W2156146072","https://openalex.org/W2159290663","https://openalex.org/W2168493061","https://openalex.org/W2168980558","https://openalex.org/W2228674556","https://openalex.org/W2269105564","https://openalex.org/W2283817422","https://openalex.org/W2296111744","https://openalex.org/W2404147237","https://openalex.org/W2916535084","https://openalex.org/W2917688842","https://openalex.org/W6603264027","https://openalex.org/W6677973343","https://openalex.org/W6712942139"],"related_works":["https://openalex.org/W4301342010","https://openalex.org/W158465921","https://openalex.org/W2261315194","https://openalex.org/W2099033952","https://openalex.org/W2520872336","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W127416991","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"Expressive":[0],"synthesis":[1,75,105,136,178,187,223],"from":[2,67,197,254],"text":[3,14,182,255],"is":[4,15,34,42,150,159,180,189,195,206,247],"a":[5,85,98,114,126,184,260],"challenging":[6],"problem.":[7],"There":[8],"are":[9,81,92,122],"two":[10,79,140],"issues.":[11],"First,":[12],"read":[13],"often":[16],"highly":[17,63],"expressive":[18,31,50,73,111,134,148,164,186,193,204,221,252],"to":[19,44,47,70,161,249,269],"convey":[20],"the":[21,26,30,49,57,110,117,120,133,144,147,156,163,167,171,174,177,192,198,203,220,231,234,251,265],"emotion":[22,91],"and":[23,90,116,155,183,208],"scenario":[24],"in":[25,94,139,166,217,226],"text.":[27,199],"Second,":[28],"since":[29],"training":[32,101],"speech":[33,74,104,135,222,236],"not":[35],"always":[36],"available":[37],"for":[38,109,237,256],"different":[39,211,238],"speakers,":[40],"it":[41,246],"necessary":[43],"develop":[45],"methods":[46],"share":[48],"information":[51,149,165,205],"over":[52,210],"speakers.":[53,212,239],"This":[54],"paper":[55,242],"investigates":[56],"approach":[58],"of":[59,78,97,113,119,128,176,233],"using":[60,125,259],"very":[61],"expressive,":[62],"diverse":[64],"audiobook":[65],"data":[66,154],"multiple":[68,257],"speakers":[69,258],"build":[71],"an":[72],"system.":[76,106],"Both":[77],"problems":[80],"addressed":[82],"by":[83,152],"considering":[84],"factorized":[86],"framework":[87],"where":[88,191],"speaker":[89,115,121,271],"modeled":[93],"separate":[95],"sub-spaces":[96,108],"cluster":[99],"adaptive":[100],"(CAT)":[102],"parametric":[103],"The":[107],"state":[112,194],"characteristics":[118],"jointly":[123],"trained":[124],"set":[127],"audiobooks.":[129],"In":[130,143,170,200],"this":[131,227,241],"work,":[132],"system":[137,179,188],"works":[138],"distinct":[141],"modes.":[142],"first":[145],"mode,":[146,173],"given":[151],"audio":[153,168],"adaptation":[157],"method":[158,224],"used":[160],"extract":[162],"data.":[169],"second":[172],"input":[175],"plain":[181],"full":[185],"examined":[190],"predicted":[196],"both":[201,218],"modes,":[202,219],"shared":[207],"transplanted":[209],"Experimental":[213],"results":[214],"show":[215],"that":[216],"proposed":[225],"work":[228],"significantly":[229],"improves":[230],"expressiveness":[232],"synthetic":[235],"Finally,":[240],"also":[243],"examines":[244],"whether":[245,264],"possible":[248],"predict":[250],"states":[253],"single":[261],"model,":[262],"or":[263],"prediction":[266],"process":[267],"needs":[268],"be":[270],"specific.":[272]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}