{"id":"https://openalex.org/W2100340603","doi":"https://doi.org/10.1109/jstsp.2010.2079315","title":"Measuring the Gap Between HMM-Based ASR and TTS","display_name":"Measuring the Gap Between HMM-Based ASR and TTS","publication_year":2010,"publication_date":"2010-09-29","ids":{"openalex":"https://openalex.org/W2100340603","doi":"https://doi.org/10.1109/jstsp.2010.2079315","mag":"2100340603"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2010.2079315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2010.2079315","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/c5e1917f-790a-4075-94af-9a6073da36d9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5105301736","display_name":"John Dines","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"John Dines","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","Centre du Parc Martigny, IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Centre du Parc Martigny, IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"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/I2802581871","display_name":"Edinburgh Cancer Research","ror":"https://ror.org/05a7t9b67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I2802581871","https://openalex.org/I98677209"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]},{"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":["CH","GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["Centre of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","Centre du Parc Martigny, IDIAP Res. Inst., Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I2802581871","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre du Parc Martigny, IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"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/I2802581871","display_name":"Edinburgh Cancer Research","ror":"https://ror.org/05a7t9b67","country_code":"GB","type":"facility","lineage":["https://openalex.org/I2801316944","https://openalex.org/I2802581871","https://openalex.org/I98677209"]},{"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":["Centre of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","Centre for Speech Technol. Res. (CSTR), Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research (CSTR), University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I2802581871","https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res. (CSTR), Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4121,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.96148213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4","issue":"6","first_page":"1046","last_page":"1058"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9929999709129333,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9001237154006958},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7965717315673828},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7354674339294434},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4803522825241089},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.47816213965415955},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.47392043471336365},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46172159910202026},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.4486522674560547},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4400462508201599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43712249398231506},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4164499044418335},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39222726225852966},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.2938155233860016}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9001237154006958},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965717315673828},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7354674339294434},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4803522825241089},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.47816213965415955},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.47392043471336365},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46172159910202026},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.4486522674560547},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4400462508201599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43712249398231506},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4164499044418335},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39222726225852966},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2938155233860016},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jstsp.2010.2079315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2010.2079315","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/c5e1917f-790a-4075-94af-9a6073da36d9","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c5e1917f-790a-4075-94af-9a6073da36d9","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dines, J, Yamagishi, J & King, S 2010, 'Measuring the gap between HMM-Based ASR and TTS', IEEE Journal of Selected Topics in Signal Processing, vol. 4, no. 6, pp. 1046-1058. https://doi.org/10.1109/JSTSP.2010.2079315","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:infoscience.epfl.ch:153584","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/153584","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"Text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/c5e1917f-790a-4075-94af-9a6073da36d9","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c5e1917f-790a-4075-94af-9a6073da36d9","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dines, J, Yamagishi, J & King, S 2010, 'Measuring the gap between HMM-Based ASR and TTS', IEEE Journal of Selected Topics in Signal Processing, vol. 4, no. 6, pp. 1046-1058. https://doi.org/10.1109/JSTSP.2010.2079315","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":88,"referenced_works":["https://openalex.org/W32588098","https://openalex.org/W51508392","https://openalex.org/W63250186","https://openalex.org/W77631327","https://openalex.org/W78363856","https://openalex.org/W83104336","https://openalex.org/W102093577","https://openalex.org/W167159165","https://openalex.org/W181114153","https://openalex.org/W284180566","https://openalex.org/W1513877108","https://openalex.org/W1529897604","https://openalex.org/W1538748823","https://openalex.org/W1553129813","https://openalex.org/W1564152904","https://openalex.org/W1573315856","https://openalex.org/W1580849279","https://openalex.org/W1593598571","https://openalex.org/W1599512239","https://openalex.org/W1600722501","https://openalex.org/W1833981795","https://openalex.org/W1846837356","https://openalex.org/W1949738355","https://openalex.org/W1963627370","https://openalex.org/W1976891543","https://openalex.org/W1983628629","https://openalex.org/W1984905644","https://openalex.org/W1989337816","https://openalex.org/W1995552268","https://openalex.org/W2000513720","https://openalex.org/W2002342963","https://openalex.org/W2019395288","https://openalex.org/W2049686551","https://openalex.org/W2054264739","https://openalex.org/W2069976350","https://openalex.org/W2072128103","https://openalex.org/W2076618452","https://openalex.org/W2081976287","https://openalex.org/W2090861223","https://openalex.org/W2093450784","https://openalex.org/W2098152933","https://openalex.org/W2100340603","https://openalex.org/W2100969003","https://openalex.org/W2106004777","https://openalex.org/W2106792148","https://openalex.org/W2107223151","https://openalex.org/W2107860279","https://openalex.org/W2111194146","https://openalex.org/W2117418893","https://openalex.org/W2119929864","https://openalex.org/W2120605154","https://openalex.org/W2121178298","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2136922672","https://openalex.org/W2139943858","https://openalex.org/W2142416747","https://openalex.org/W2143361917","https://openalex.org/W2147880316","https://openalex.org/W2148154194","https://openalex.org/W2150612204","https://openalex.org/W2150907703","https://openalex.org/W2153914468","https://openalex.org/W2154920538","https://openalex.org/W2159632499","https://openalex.org/W2162351465","https://openalex.org/W2164597369","https://openalex.org/W2165143604","https://openalex.org/W2204452154","https://openalex.org/W2296704011","https://openalex.org/W2400063444","https://openalex.org/W2484208911","https://openalex.org/W2543977149","https://openalex.org/W3142087749","https://openalex.org/W4205130185","https://openalex.org/W4285719527","https://openalex.org/W4301420498","https://openalex.org/W6602582525","https://openalex.org/W6603374673","https://openalex.org/W6610316872","https://openalex.org/W6630780049","https://openalex.org/W6633741138","https://openalex.org/W6676227212","https://openalex.org/W6676358011","https://openalex.org/W6680838236","https://openalex.org/W6682082992","https://openalex.org/W6682398751","https://openalex.org/W6865107258"],"related_works":["https://openalex.org/W2140536630","https://openalex.org/W2391730868","https://openalex.org/W2759814045","https://openalex.org/W2038801705","https://openalex.org/W2338806053","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"The":[0,18],"EMIME":[1],"European":[2],"project":[3],"is":[4,23],"conducting":[5],"research":[6],"in":[7,30,154],"the":[8,27,42,60,126,133,155],"development":[9],"of":[10,44,54,59,86,89,157],"technologies":[11],"for":[12],"mobile,":[13],"personalized":[14],"speech-to-speech":[15],"translation":[16],"systems.":[17],"hidden":[19],"Markov":[20],"model":[21,129],"(HMM)":[22],"being":[24],"used":[25],"as":[26],"underlying":[28],"technology":[29],"both":[31],"automatic":[32],"speech":[33],"recognition":[34],"(ASR)":[35],"and":[36,71,76,84,98,109,114,118,137],"text-to-speech":[37],"synthesis":[38],"(TTS)":[39],"components;":[40],"thus,":[41],"investigation":[43,156],"unified":[45,159],"statistical":[46,128],"modeling":[47,160],"approaches":[48],"has":[49],"become":[50],"an":[51],"implicit":[52],"goal":[53],"our":[55],"research.":[56],"As":[57],"one":[58],"first":[61],"steps":[62],"towards":[63],"this":[64,79],"goal,":[65],"we":[66,81],"have":[67,92],"been":[68,93],"investigating":[69],"commonalities":[70],"differences":[72],"between":[73],"HMM-based":[74],"ASR":[75,97,136],"TTS.":[77],"In":[78],"paper,":[80],"present":[82],"results":[83,122],"analysis":[85],"a":[87,148],"series":[88],"experiments":[90],"that":[91],"conducted":[94],"on":[95],"English":[96],"TTS":[99,138],"systems":[100],"measuring":[101],"their":[102],"performance":[103,139],"with":[104],"respect":[105],"to":[106,151],"phone":[107],"set":[108],"lexicon,":[110],"acoustic":[111],"feature":[112],"type":[113],"dimensionality,":[115],"HMM":[116],"topology,":[117],"speaker":[119],"adaptation.":[120],"Our":[121],"show":[123],"that,":[124],"although":[125],"fundamental":[127],"may":[130],"be":[131,152],"essentially":[132],"same,":[134],"optimal":[135],"often":[140],"demands":[141],"diametrically":[142],"opposed":[143],"system":[144],"designs.":[145],"This":[146],"represents":[147],"major":[149],"challenge":[150],"addressed":[153],"such":[158],"approaches.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}