{"id":"https://openalex.org/W2168609041","doi":"https://doi.org/10.1109/icassp.2013.6639192","title":"Factorized context modelling for Text-to-Speech synthesis","display_name":"Factorized context modelling for Text-to-Speech synthesis","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2168609041","doi":"https://doi.org/10.1109/icassp.2013.6639192","mag":"2168609041"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/36378178-223e-4f9d-a7fc-73bbea7fe062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100618443","display_name":"Heng Lu","orcid":"https://orcid.org/0009-0009-9236-8825"},"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":"Heng Lu","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":null,"first_page":"7849","last_page":"7853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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":0.7696495056152344},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6336274743080139},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5953115224838257},{"id":"https://openalex.org/keywords/dynamic-bayesian-network","display_name":"Dynamic Bayesian network","score":0.585422933101654},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.5713016390800476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556742548942566},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5316819548606873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5305360555648804},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5104876756668091},{"id":"https://openalex.org/keywords/factorial","display_name":"Factorial","score":0.45682433247566223},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.4200981557369232},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41993623971939087},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4179849624633789},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4169202148914337},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3301883041858673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16300389170646667},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12469109892845154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7696495056152344},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6336274743080139},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5953115224838257},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.585422933101654},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.5713016390800476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556742548942566},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5316819548606873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5305360555648804},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5104876756668091},{"id":"https://openalex.org/C183763347","wikidata":"https://www.wikidata.org/wiki/Q120976","display_name":"Factorial","level":2,"score":0.45682433247566223},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.4200981557369232},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41993623971939087},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4179849624633789},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4169202148914337},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3301883041858673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16300389170646667},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12469109892845154},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2013.6639192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.4282","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.4282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.inf.ed.ac.uk/downloads/publications/2013/IC13HengSimon.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/36378178-223e-4f9d-a7fc-73bbea7fe062","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/36378178-223e-4f9d-a7fc-73bbea7fe062","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, H & King, S 2013, Factorized context modelling for Text-to-Speech synthesis. in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. Institute of Electrical and Electronics Engineers, pp. 7849-7853. https://doi.org/10.1109/ICASSP.2013.6639192","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/36378178-223e-4f9d-a7fc-73bbea7fe062","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6639192","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":{"id":"pmh:oai:pure.ed.ac.uk:openaire/36378178-223e-4f9d-a7fc-73bbea7fe062","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/36378178-223e-4f9d-a7fc-73bbea7fe062","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Lu, H & King, S 2013, Factorized context modelling for Text-to-Speech synthesis. in Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International Conference on. Institute of Electrical and Electronics Engineers, pp. 7849-7853. https://doi.org/10.1109/ICASSP.2013.6639192","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W41895731","https://openalex.org/W95152782","https://openalex.org/W1512429158","https://openalex.org/W1537659559","https://openalex.org/W1539337024","https://openalex.org/W1564633198","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W2004590799","https://openalex.org/W2025638820","https://openalex.org/W2069631319","https://openalex.org/W2101859041","https://openalex.org/W2110575115","https://openalex.org/W2120804163","https://openalex.org/W2122678358","https://openalex.org/W2127846433","https://openalex.org/W2143321035","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2170980774","https://openalex.org/W2171265988","https://openalex.org/W3150444200","https://openalex.org/W3151884159","https://openalex.org/W4297792526","https://openalex.org/W6601685338","https://openalex.org/W6603838645","https://openalex.org/W6630838124","https://openalex.org/W6632529224","https://openalex.org/W6641076745","https://openalex.org/W6678053104","https://openalex.org/W6681122356","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W1964038743","https://openalex.org/W3128072696","https://openalex.org/W2578973671","https://openalex.org/W2215058820","https://openalex.org/W2097663773","https://openalex.org/W1602184117","https://openalex.org/W2413421635","https://openalex.org/W2511198839","https://openalex.org/W1966557338","https://openalex.org/W2366931106"],"abstract_inverted_index":{"Because":[0],"speech":[1,20],"units":[2],"are":[3,13,39,132],"so":[4],"context-dependent,":[5],"a":[6,66,83,104,108,129],"large":[7],"number":[8],"of":[9,47,55,71,91,122,128,144],"linguistic":[10],"context":[11,73,124],"features":[12,48],"generally":[14],"used":[15,40],"by":[16],"HMM-based":[17],"Text-to-Speech":[18],"(TTS)":[19],"synthesis":[21],"systems,":[22],"via":[23],"context-dependent":[24],"models.":[25],"Since":[26],"it":[27],"is":[28,59],"impossible":[29],"to":[30,41,63,76,119],"train":[31],"separate":[32],"models":[33],"for":[34],"every":[35],"context,":[36],"decision":[37,57],"trees":[38],"discover":[42],"the":[43,56,72,77,96,123,137,141],"most":[44],"important":[45],"combinations":[46],"that":[49,136],"should":[50],"be":[51],"modelled.":[52],"The":[53,126],"task":[54],"tree":[58],"very":[60,67],"hard":[61],"-":[62,79],"generalize":[64],"from":[65],"small":[68],"observed":[69],"part":[70],"feature":[74,102],"space":[75,98],"rest":[78],"and":[80],"they":[81,86,94],"have":[82],"major":[84],"weakness:":[85],"cannot":[87],"directly":[88],"take":[89],"advantage":[90],"factorial":[92,142],"properties:":[93],"subdivide":[95],"model":[97,138],"based":[99,113],"on":[100],"one":[101],"at":[103],"time.":[105],"We":[106],"propose":[107],"Dynamic":[109],"Bayesian":[110],"Network":[111],"(DBN)":[112],"Mixed":[114],"Memory":[115],"Markov":[116],"Model":[117],"(MMMM)":[118],"provide":[120],"factorization":[121],"space.":[125,146],"results":[127],"listening":[130],"test":[131],"provided":[133],"as":[134],"evidence":[135],"successfully":[139],"learns":[140],"nature":[143],"this":[145]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}