{"id":"https://openalex.org/W2395689816","doi":"https://doi.org/10.1109/icassp.2016.7472660","title":"Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis","display_name":"Testing the consistency assumption: Pronunciation variant forced alignment in read and spontaneous speech synthesis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2395689816","doi":"https://doi.org/10.1109/icassp.2016.7472660","mag":"2395689816"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/41910/1/dall2016testing.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["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":"middle","author":{"id":"https://openalex.org/A5025737662","display_name":"Sandrine Brognaux","orcid":null},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]},{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Sandrine Brognaux","raw_affiliation_strings":["Cental, ICTEAM, Universite Catholique de Louvain, Belgium","TCTS Lab, University of Mons, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cental, ICTEAM, Universite Catholique de Louvain, Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"TCTS Lab, University of Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","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":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"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":"Cassia Valentini-Botinhao","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":"middle","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"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":"Gustav Eje Henter","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":"middle","author":{"id":"https://openalex.org/A5045037642","display_name":"Julia Hirschberg","orcid":"https://orcid.org/0000-0003-0689-7616"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Hirschberg","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"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":"Junichi Yamagishi","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":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"5155","last_page":"5159"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9965000152587891,"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":0.7227665185928345},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6896780133247375},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6846886873245239},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6607532501220703},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5629011988639832},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5373313426971436},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5254016518592834},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47702667117118835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39852988719940186},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21480125188827515}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227665185928345},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6896780133247375},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6846886873245239},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6607532501220703},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5629011988639832},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5373313426971436},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5254016518592834},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47702667117118835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39852988719940186},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21480125188827515},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2016.7472660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/41910","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/41910","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/41910/1/dall2016testing.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","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":"IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings (2016-03-20)","raw_type":"http://purl.org/coar/resource_type/c_6501"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f9fb25b6-9e29-4930-8f0d-a6e60cb42dd5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f9fb25b6-9e29-4930-8f0d-a6e60cb42dd5","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f9fb25b6-9e29-4930-8f0d-a6e60cb42dd5","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/f9fb25b6-9e29-4930-8f0d-a6e60cb42dd5","pdf_url":null,"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":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:orbi.umons.ac.be:20.500.12907/41910","is_oa":true,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/41910","pdf_url":"https://orbi.umons.ac.be/bitstream/20.500.12907/41910/1/dall2016testing.pdf","source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","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":"IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings (2016-03-20)","raw_type":"http://purl.org/coar/resource_type/c_6501"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions"}],"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/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2395689816.pdf","grobid_xml":"https://content.openalex.org/works/W2395689816.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W94553846","https://openalex.org/W165417294","https://openalex.org/W180253589","https://openalex.org/W832263738","https://openalex.org/W1511205537","https://openalex.org/W1562782443","https://openalex.org/W1598391929","https://openalex.org/W1630569004","https://openalex.org/W1776535839","https://openalex.org/W1833998246","https://openalex.org/W1993617199","https://openalex.org/W2005768155","https://openalex.org/W2095263712","https://openalex.org/W2130628335","https://openalex.org/W2132470403","https://openalex.org/W2145247325","https://openalex.org/W2155576284","https://openalex.org/W2168584209","https://openalex.org/W2281596517","https://openalex.org/W2396600922","https://openalex.org/W2572080576","https://openalex.org/W2598976329","https://openalex.org/W2599840324","https://openalex.org/W6603816724","https://openalex.org/W6607341252","https://openalex.org/W6633521006","https://openalex.org/W6635989558","https://openalex.org/W6636567668","https://openalex.org/W6638112514","https://openalex.org/W6684513021","https://openalex.org/W6712596578"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"Forced":[0],"alignment":[1,62,93,126],"for":[2,96,107],"speech":[3,70],"synthesis":[4],"traditionally":[5],"aligns":[6],"a":[7,84],"phoneme":[8,72,104],"sequence":[9,18,73],"predetermined":[10],"by":[11],"the":[12,36,48,61,133],"front-end":[13],"text":[14],"processing":[15],"system.":[16],"This":[17],"is":[19,26,35,74,80,99],"not":[20,42],"altered":[21],"during":[22],"alignment,":[23],"i.e.,":[24],"it":[25],"forced,":[27],"despite":[28,131],"possibly":[29],"being":[30],"faulty.":[31],"The":[32],"consistency":[33,134],"assumption":[34,37],"that":[38,59,78,119],"these":[39],"mistakes":[40,49],"do":[41],"degrade":[43],"models,":[44],"as":[45,47],"long":[46],"are":[50],"consistent":[51],"across":[52],"training":[53],"and":[54,68,77],"synthesis.":[55],"We":[56],"present":[57],"evidence":[58],"in":[60,102],"of":[63,110,115],"both":[64,108],"standard":[65,129],"read":[66],"prompts":[67],"spontaneous":[69,120],"this":[71,79,124],"often":[75],"wrong,":[76],"likely":[81],"to":[82],"have":[83],"negative":[85],"impact":[86],"on":[87,123],"acoustic":[88],"models.":[89],"A":[90,112],"lattice-based":[91],"forced":[92],"system":[94],"allowing":[95],"pronunciation":[97],"variation":[98],"implemented,":[100],"resulting":[101],"improved":[103,125,128],"identity":[105],"accuracy":[106],"types":[109],"speech.":[111],"perceptual":[113],"evaluation":[114],"HMM-based":[116],"voices":[117],"showed":[118],"models":[121],"trained":[122],"also":[127],"synthesis,":[130],"breaking":[132],"assumption.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}