{"id":"https://openalex.org/W2295934277","doi":"https://doi.org/10.21437/interspeech.2014-318","title":"Generating multiple-accent pronunciations for TTS using joint sequence model interpolation","display_name":"Generating multiple-accent pronunciations for TTS using joint sequence model interpolation","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2295934277","doi":"https://doi.org/10.21437/interspeech.2014-318","mag":"2295934277"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-318","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","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/A5038473184","display_name":"BalaKrishna Kolluru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"BalaKrishna Kolluru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031222393","display_name":"Vincent Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1273","last_page":"1277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.8650558590888977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6794884204864502},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6237455606460571},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6230142712593079},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5933515429496765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5689070224761963},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5594682097434998},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5126611590385437},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.49240148067474365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48934000730514526},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4548722505569458},{"id":"https://openalex.org/keywords/grapheme","display_name":"Grapheme","score":0.42844358086586},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4058336615562439},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32696133852005005},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23758545517921448}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8650558590888977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6794884204864502},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6237455606460571},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6230142712593079},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5933515429496765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5689070224761963},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5594682097434998},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5126611590385437},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.49240148067474365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48934000730514526},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4548722505569458},{"id":"https://openalex.org/C2776779415","wikidata":"https://www.wikidata.org/wiki/Q2545446","display_name":"Grapheme","level":3,"score":0.42844358086586},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4058336615562439},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32696133852005005},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23758545517921448},{"id":"https://openalex.org/C30080830","wikidata":"https://www.wikidata.org/wiki/Q169917","display_name":"Graphene","level":2,"score":0.0},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-318","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-318","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:788328","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/788328/","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W659550629","https://openalex.org/W1506806321","https://openalex.org/W1909550130","https://openalex.org/W1966083358","https://openalex.org/W2005768155","https://openalex.org/W2083053451","https://openalex.org/W2084974857","https://openalex.org/W2090755665","https://openalex.org/W2145247325","https://openalex.org/W2153058382","https://openalex.org/W2175139733","https://openalex.org/W2228674556","https://openalex.org/W2394668095","https://openalex.org/W2406225780"],"related_works":["https://openalex.org/W2506515307","https://openalex.org/W2060656088","https://openalex.org/W2183593636","https://openalex.org/W4391124013","https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497","https://openalex.org/W2080578089","https://openalex.org/W4387715848","https://openalex.org/W2179005426"],"abstract_inverted_index":{"Standard":[0],"grapheme-to-phoneme":[1],"(G2P)":[2],"systems":[3],"are":[4,84],"trained":[5],"using":[6,132],"a":[7,15,20,31,35,46,61,75,108,166],"homogeneous":[8],"lexicon,":[9],"for":[10,51,81,121],"example":[11],"one":[12],"associated":[13],"with":[14],"particular":[16],"accent.":[17],"In":[18],"practice,":[19],"synthesis":[21,63],"system":[22],"may":[23],"be":[24],"required":[25],"to":[26,59,117,156],"handle":[27],"multiple":[28],"accents.":[29,78],"Furthermore,":[30],"speaker":[32],"rarely":[33],"has":[34],"pure":[36],"accent;":[37],"accents":[38,162],"vary":[39],"continuously":[40],"within":[41],"and":[42,140],"between":[43],"regions":[44],"of":[45,77,93,99,127,168],"country.":[47],"Generating":[48],"phonetic":[49],"sequences":[50],"each":[52],"accent":[53,104,120,134,147],"is":[54,65,115,130,150,154],"possible,":[55],"but":[56],"combining":[57],"them":[58],"yield":[60],"single":[62],"pronunciation":[64],"highly":[66],"challenging.":[67],"To":[68],"address":[69],"this":[70,72,111,128],"problem,":[71],"paper":[73],"considers":[74],"space":[76,135],"The":[79,125],"bases":[80],"these":[82,100,161],"spaces":[83],"defined":[85,136],"by":[86,137],"statistical":[87],"G2P":[88],"models":[89,101],"in":[90,110],"the":[91,103,119,146],"form":[92],"graphone":[94],"models.":[95],"A":[96],"linear":[97],"combination":[98],"define":[102],"space.":[105],"By":[106,143],"selecting":[107],"point":[109],"continuous":[112],"space,":[113,148],"it":[114,149,153],"possible":[116,155],"specify":[118],"an":[122,133],"individual":[123],"speaker.":[124],"performance":[126],"approach":[129],"evaluated":[131],"American,":[138],"Scottish":[139],"British":[141],"English.":[142],"moving":[144],"around":[145],"shown":[151],"that":[152],"synthesize":[157],"speech":[158],"from":[159],"all":[160],"as":[163,165],"well":[164],"range":[167],"intermediate":[169],"points.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}