{"id":"https://openalex.org/W2025638820","doi":"https://doi.org/10.1109/tasl.2012.2187195","title":"Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization","display_name":"Statistical Parametric Speech Synthesis Based on Speaker and Language Factorization","publication_year":2012,"publication_date":"2012-02-07","ids":{"openalex":"https://openalex.org/W2025638820","doi":"https://doi.org/10.1109/tasl.2012.2187195","mag":"2025638820"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2187195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2187195","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"H. Zen","raw_affiliation_strings":["Google, London, UK","was with Toshiba Research Europe, Cambridge, U.K. He is now with Google, London, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, London, UK","institution_ids":["https://openalex.org/I4210113297"]},{"raw_affiliation_string":"was with Toshiba Research Europe, Cambridge, U.K. He is now with Google, London, U.K","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075928867","display_name":"Norbert Braunschweiler","orcid":"https://orcid.org/0000-0003-1388-440X"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"N. Braunschweiler","raw_affiliation_strings":["Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004649927","display_name":"Sabine Buchholz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Buchholz","raw_affiliation_strings":["SynapseWork, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SynapseWork, Cambridge, UK","institution_ids":[]}]},{"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/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"M. J. F. Gales","raw_affiliation_strings":["Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032046290","display_name":"K.M. Knill","orcid":"https://orcid.org/0000-0003-1292-2769"},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"K. Knill","raw_affiliation_strings":["Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012719765","display_name":"Sacha Krstulovi\u0107","orcid":"https://orcid.org/0000-0003-4015-4445"},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210142256","display_name":"Nuance Communications (United Kingdom)","ror":"https://ror.org/03ae66d75","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210142256"]}],"countries":["AT","GB"],"is_corresponding":false,"raw_author_name":"S. Krstulovic","raw_affiliation_strings":["Nuance Communications, Cambridge, UK","Nuance Commun., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Cambridge, UK","institution_ids":["https://openalex.org/I4210142256"]},{"raw_affiliation_string":"Nuance Commun., Cambridge, UK","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"J. Latorre","raw_affiliation_strings":["Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Toshiba Res. Eur. Cambridge Res. Lab., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.8325,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.99297407,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"20","issue":"6","first_page":"1713","last_page":"1724"},"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":0.9977999925613403,"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":0.9958000183105469,"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":0.819094181060791},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5988782048225403},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5539815425872803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5450116395950317},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4984269142150879},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4749888479709625},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4672310948371887},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4474751651287079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4315696954727173},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36678531765937805},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3662516474723816},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14970111846923828},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13321399688720703},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07913997769355774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.819094181060791},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5988782048225403},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5539815425872803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5450116395950317},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4984269142150879},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4749888479709625},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4672310948371887},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4474751651287079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4315696954727173},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36678531765937805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3662516474723816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14970111846923828},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13321399688720703},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07913997769355774},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2012.2187195","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2187195","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:generic.eprints.org:436980","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/436980/","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W35069904","https://openalex.org/W66627554","https://openalex.org/W80543058","https://openalex.org/W88751538","https://openalex.org/W102093577","https://openalex.org/W113498433","https://openalex.org/W118315650","https://openalex.org/W127087823","https://openalex.org/W202820833","https://openalex.org/W344150399","https://openalex.org/W1499275966","https://openalex.org/W1512429158","https://openalex.org/W1564152904","https://openalex.org/W1572989473","https://openalex.org/W1599512239","https://openalex.org/W1600722501","https://openalex.org/W1660564604","https://openalex.org/W1963854073","https://openalex.org/W1995565802","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2003105834","https://openalex.org/W2036740752","https://openalex.org/W2069631319","https://openalex.org/W2114010348","https://openalex.org/W2129142580","https://openalex.org/W2131650634","https://openalex.org/W2135145707","https://openalex.org/W2142980177","https://openalex.org/W2143361917","https://openalex.org/W2147143213","https://openalex.org/W2148331133","https://openalex.org/W2154920538","https://openalex.org/W2158086337","https://openalex.org/W2160084280","https://openalex.org/W2165108269","https://openalex.org/W2292984643","https://openalex.org/W2294327763","https://openalex.org/W2309282333","https://openalex.org/W2407077870","https://openalex.org/W2740537351","https://openalex.org/W4285719527","https://openalex.org/W4301420498","https://openalex.org/W6602682705","https://openalex.org/W6603264027","https://openalex.org/W6604792588","https://openalex.org/W6611766843","https://openalex.org/W6630838124","https://openalex.org/W6633741138","https://openalex.org/W6680838236","https://openalex.org/W6681160539","https://openalex.org/W6713832071"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2162158162","https://openalex.org/W2904846757","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479"],"abstract_inverted_index":{"An":[0],"increasingly":[1],"common":[2],"scenario":[3],"in":[4,48,60,109,122,129],"building":[5],"speech":[6,97,121],"synthesis":[7,98,118],"and":[8,33,40,51,133],"recognition":[9],"systems":[10],"is":[11],"training":[12],"on":[13,27,68,87,94],"inhomogeneous":[14],"data.":[15],"This":[16],"paper":[17],"proposes":[18],"a":[19,117,123,130,136],"new":[20,137],"framework":[21,103],"for":[22],"estimating":[23],"hidden":[24],"Markov":[25],"models":[26],"data":[28,50,62,105],"containing":[29],"both":[30],"multiple":[31,34,107],"speakers":[32,108],"languages.":[35],"The":[36],"proposed":[37,102],"framework,":[38],"speaker":[39,80,126],"language":[41,124],"factorization,":[42],"attempts":[43],"to":[44,112,135],"factorize":[45],"speaker-/language-specific":[46],"characteristics":[47,81,127],"the":[49,61,101],"then":[52],"model":[53],"them":[54],"using":[55,125],"separate":[56],"transforms.":[57],"Language-specific":[58],"factors":[59],"are":[63,82],"represented":[64],"by":[65,79,84],"transforms":[66,85],"based":[67,86],"cluster":[69],"mean":[70],"interpolation":[71],"with":[72],"cluster-dependent":[73],"decision":[74],"trees.":[75],"Acoustic":[76],"variations":[77],"caused":[78],"handled":[83],"constrained":[88],"maximum-likelihood":[89],"linear":[90],"regression.":[91],"Experimental":[92],"results":[93],"statistical":[95],"parametric":[96],"show":[99],"that":[100],"enables":[104],"from":[106],"different":[110,131],"languages":[111],"be":[113],"used":[114],"to:":[115],"train":[116],"system;":[119],"synthesize":[120],"estimated":[128],"language;":[132],"adapt":[134],"language.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":13},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
