{"id":"https://openalex.org/W1531020154","doi":"https://doi.org/10.21437/interspeech.2014-320","title":"A flexible front-end for HTS","display_name":"A flexible front-end for HTS","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W1531020154","doi":"https://doi.org/10.21437/interspeech.2014-320","mag":"1531020154"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-320","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-320","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/19912602/i14_1283.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007820415","display_name":"Matthew P. Aylett","orcid":"https://orcid.org/0000-0001-7057-0525"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Matthew P. Aylett","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087783960","display_name":"Rasmus Dall","orcid":null},"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":"Rasmus Dall","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["Apple (Israel), Herzliya, Israel"],"affiliations":[{"raw_affiliation_string":"Apple (Israel), Herzliya, Israel","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gustav Eje Henter","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"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":"Thomas Merritt","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007820415"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.844,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79907773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1283","last_page":"1287"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9973999857902527,"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/front-and-back-ends","display_name":"Front and back ends","score":0.8173754215240479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.762233316898346},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6250253915786743},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.622567355632782},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5647361874580383},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.5621778964996338},{"id":"https://openalex.org/keywords/front","display_name":"Front (military)","score":0.44935888051986694},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4439356327056885},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2614782452583313},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10175177454948425},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.07248103618621826}],"concepts":[{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.8173754215240479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762233316898346},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6250253915786743},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.622567355632782},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5647361874580383},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5621778964996338},{"id":"https://openalex.org/C2777551076","wikidata":"https://www.wikidata.org/wiki/Q842332","display_name":"Front (military)","level":2,"score":0.44935888051986694},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4439356327056885},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2614782452583313},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10175177454948425},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.07248103618621826},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2014-320","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-320","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:pure.ed.ac.uk:publications/a17810b7-cb96-4bfe-b2b0-f36c8186ce9a","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2014/i14_1283.html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19912602/i14_1283.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Aylett, M, Dall, R, Ghoshal, A, Henter, G E & Merritt, T 2014, A Flexible Front-End for HTS. in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 1283-1287. < http://www.isca-speech.org/archive/interspeech_2014/i14_1283.html >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.719.4340","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.719.4340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2014/Aylett_Dall_Ghoshal_Henter_Merritt_Interspeech2014.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/a17810b7-cb96-4bfe-b2b0-f36c8186ce9a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a17810b7-cb96-4bfe-b2b0-f36c8186ce9a","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":"Aylett, M, Dall, R, Ghoshal, A, Henter, G E & Merritt, T 2014, A Flexible Front-End for HTS. in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 1283-1287. < http://www.isca-speech.org/archive/interspeech_2014/i14_1283.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/a17810b7-cb96-4bfe-b2b0-f36c8186ce9a","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2014/i14_1283.html","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19912602/i14_1283.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Aylett, M, Dall, R, Ghoshal, A, Henter, G E & Merritt, T 2014, A Flexible Front-End for HTS. in INTERSPEECH 2014 15th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 1283-1287. < http://www.isca-speech.org/archive/interspeech_2014/i14_1283.html >","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1531020154.pdf","grobid_xml":"https://content.openalex.org/works/W1531020154.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1564633198","https://openalex.org/W2099954993","https://openalex.org/W2111284386","https://openalex.org/W2395578248","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W2074777875","https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W4210368779","https://openalex.org/W2088988140","https://openalex.org/W4232652765","https://openalex.org/W2103019253","https://openalex.org/W2951529875","https://openalex.org/W2391453316"],"abstract_inverted_index":{"Parametric":[0],"speech":[1,61,76,169],"synthesis":[2,24,39,77],"techniques":[3],"depend":[4],"on":[5],"full":[6,35,110],"context":[7,36,111],"acoustic":[8,112],"models":[9,37],"generated":[10],"by":[11,154],"language":[12],"front-ends,":[13],"which":[14],"anal-yse":[15],"linguistic":[16],"and":[17,40,89,92,103],"phonetic":[18],"structure.":[19],"HTS,":[20],"the":[21,47,60,96,106,120,125,130,136],"leading":[22],"paramet-ric":[23],"system,":[25,78],"can":[26,158],"use":[27,48,81],"a":[28,50,73,86,148],"number":[29],"of":[30,49,67,82,164],"different":[31],"front-ends":[32],"to":[33,59,71,161],"generate":[34],"for":[38,100],"training.":[41],"In":[42],"this":[43],"paper":[44],"we":[45],"explore":[46],"new":[51,74],"text":[52,171],"processing":[53],"front-end":[54,98,116,123,132,140],"that":[55],"has":[56],"been":[57],"added":[58],"recognition":[62],"toolkit":[63],"Kaldi":[64],"as":[65],"part":[66],"an":[68],"ongoing":[69],"project":[70],"produce":[72],"parametric":[75,173],"Idlak.":[79],"The":[80,114],"XML":[83],"specification":[84],"files,":[85],"modular":[87],"design,":[88],"modern":[90],"coding":[91],"testing":[93],"approaches,":[94],"make":[95],"Idlak":[97,115,131,176],"ideal":[99],"adding,":[101],"altering":[102],"experi-menting":[104],"with":[105,135],"contexts":[107],"used":[108],"in":[109,124,151],"models.":[113],"was":[117],"evaluated":[118],"against":[119],"standard":[121],"Festival":[122,139],"HTS":[126],"system.":[127],"Results":[128],"from":[129],"compare":[133],"well":[134],"more":[137],"mature":[138],"(Idlak-2.83":[141],"MOS":[142],"vs":[143],"Festival-":[144],"2.85":[145],"MOS),":[146],"although":[147],"slight":[149],"reduction":[150],"naturalness":[152],"perceived":[153],"non-native":[155],"English":[156],"speakers":[157],"be":[159],"attributed":[160],"Festival\u2019s":[162],"insertion":[163],"non-punctuated":[165],"pauses.":[166],"Index":[167],"Terms:":[168],"synthesis,":[170,174],"processing,":[172],"Kaldi,":[175]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
