{"id":"https://openalex.org/W2128066925","doi":"https://doi.org/10.21437/interspeech.2009-598","title":"Speech synthesis without a phone inventory","display_name":"Speech synthesis without a phone inventory","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W2128066925","doi":"https://doi.org/10.21437/interspeech.2009-598","mag":"2128066925"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/3909","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":false,"raw_author_name":"Matthew P. Aylett","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]},{"author_position":"middle","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":["School of Philosophy Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy Psychology and Language Sciences","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Philosophy, Psychology and Language Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Philosophy, Psychology and Language Sciences","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2087","last_page":"2090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9973000288009644,"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/phone","display_name":"Phone","score":0.8271627426147461},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7511707544326782},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6805409789085388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5889964699745178},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5822207927703857},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5528207421302795},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5185104608535767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48535457253456116},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.46216344833374023},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34109967947006226},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20580795407295227},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12797141075134277}],"concepts":[{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.8271627426147461},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511707544326782},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6805409789085388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5889964699745178},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5822207927703857},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5528207421302795},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5185104608535767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48535457253456116},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.46216344833374023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34109967947006226},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20580795407295227},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12797141075134277},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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.2009-598","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3909","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3909","pdf_url":"http://hdl.handle.net/1842/3909","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c1babb29-9fbc-4379-ad38-6d2200e37227","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c1babb29-9fbc-4379-ad38-6d2200e37227","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15133080/Speech_synthesis_without_a_phone_inventory.pdf","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":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.147.9075","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.147.9075","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/2009/ma_interspeech09.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3909","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3909","pdf_url":"http://hdl.handle.net/1842/3909","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G1544209593","display_name":"Automatically-determined Unit Inventories for Unit Selection Text-to-Speech Synthesis","funder_award_id":"EP/D058139/1","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2128066925.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1746156","https://openalex.org/W1541208205","https://openalex.org/W1548827369","https://openalex.org/W1580837119","https://openalex.org/W2001141328","https://openalex.org/W2049686551","https://openalex.org/W2101392473","https://openalex.org/W2118841860","https://openalex.org/W2122395445","https://openalex.org/W2165712214","https://openalex.org/W2165856656"],"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/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W4220683390","https://openalex.org/W2773393136"],"abstract_inverted_index":{"In":[0,21],"speech":[1,43,132],"synthesis":[2,44,141],"the":[3,84,89,93,109],"unit":[4,51,134],"inventory":[5,58],"is":[6,15],"decided":[7],"using":[8,48,68],"phonological":[9],"and":[10,18,53,71,87,104,122],"phonetic":[11],"expertise.":[12],"This":[13,107],"process":[14],"resource":[16],"intensive":[17],"potentially":[19],"sub-optimal.":[20],"this":[22],"paper":[23],"we":[24],"investigate":[25],"how":[26],"acoustic":[27],"clustering,":[28],"together":[29],"with":[30],"lexicon":[31],"constraints,":[32],"can":[33],"be":[34],"used":[35],"to":[36,101,113],"build":[37],"a":[38,61,66,73,80],"self-organised":[39,74,94,110],"inventory.":[40,75],"Six":[41],"English":[42],"systems":[45],"were":[46],"built":[47],"two":[49],"frameworks,":[50],"selection":[52],"parametric":[54,136],"HTS":[55],"for":[56,83,88],"three":[57],"conditions:":[59],"1)":[60],"traditional":[62],"phone":[63,138],"set,":[64],"2)":[65],"system":[67,91],"orthographic":[69,90,127,140],"units,":[70],"3)":[72],"A":[76],"listening":[77],"test":[78],"showed":[79],"strong":[81],"preference":[82],"classic":[85],"system,":[86],"over":[92],"system.":[95],"Results":[96],"also":[97],"varied":[98],"by":[99,126],"letter":[100],"sound":[102,128],"complexity":[103],"database":[105],"coverage.":[106],"suggests":[108],"approach":[111],"failed":[112],"generalise":[114],"pronunciation":[115],"as":[116,118],"well":[117],"introducing":[119],"noise":[120],"above":[121],"beyond":[123],"that":[124],"caused":[125],"mismatch.":[129],"Index":[130],"Terms:":[131],"synthesis,":[133,137],"selection,":[135],"inventory,":[139]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
