{"id":"https://openalex.org/W1518816749","doi":"https://doi.org/10.21437/interspeech.2009-429","title":"Measuring the gap between HMM-based ASR and TTS","display_name":"Measuring the gap between HMM-based ASR and TTS","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1518816749","doi":"https://doi.org/10.21437/interspeech.2009-429","mag":"1518816749"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-429","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-429","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://infoscience.epfl.ch/record/145971","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-Combe, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny-Combe, 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/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":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","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":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1391","last_page":"1394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8904182314872742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7753138542175293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6768022179603577},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5024263858795166},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4845794439315796},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4653720557689667},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44655317068099976},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.44045940041542053},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.43584734201431274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4345972239971161},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41520193219184875},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4147307872772217},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4103314280509949},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3402182161808014},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08049768209457397}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8904182314872742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753138542175293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6768022179603577},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5024263858795166},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4845794439315796},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4653720557689667},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44655317068099976},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.44045940041542053},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.43584734201431274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4345972239971161},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41520193219184875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4147307872772217},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4103314280509949},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3402182161808014},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08049768209457397},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":11,"locations":[{"id":"doi:10.21437/interspeech.2009-429","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-429","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:CiteSeerX.psu:10.1.1.330.7383","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.7383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2009/Dines_INTERSPEECH_2009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.2510","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.2510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2010/Dines_JSTSP_2010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.593.68","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.593.68","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2009/Dines_Idiap-RR-16-2009.pdf","raw_type":"text"},{"id":"pmh:oai:era.ed.ac.uk:1842/3955","is_oa":false,"landing_page_url":"http://hdl.handle.net/1842/3955","pdf_url":null,"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:infoscience.epfl.ch:145971","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145971","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"},{"id":"pmh:oai:infoscience.epfl.ch:146386","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146386","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"},{"id":"pmh:oai:infoscience.epfl.ch:153575","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/153575","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"},{"id":"pmh:oai:infoscience.tind.io:145971","is_oa":true,"landing_page_url":"http://publications.idiap.ch/index.php/publications/showcite/Dines_Idiap-RR-16-2009","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":null,"raw_type":"conference proceedings"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/c5e1917f-790a-4075-94af-9a6073da36d9","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c5e1917f-790a-4075-94af-9a6073da36d9","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":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f9c12fe9-2961-47b1-87ff-9982c84e8061","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f9c12fe9-2961-47b1-87ff-9982c84e8061","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":"Dines, J, Yamagishi, J & King, S 2009, Measuring the gap between HMM-based ASR and TTS. in Interspeech 2009 : 10th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 1391-1394.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:145971","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/145971","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1529897604","https://openalex.org/W1580849279","https://openalex.org/W1593598571","https://openalex.org/W1600722501","https://openalex.org/W1995552268","https://openalex.org/W2054264739"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2338806053","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W4385571610","https://openalex.org/W39235475","https://openalex.org/W2293738010","https://openalex.org/W4360995948"],"abstract_inverted_index":{"The":[0,18],"EMIME":[1],"European":[2],"project":[3],"is":[4,22],"conducting":[5],"research":[6],"in":[7,29,150],"the":[8,26,41,59,122,129,151],"development":[9],"of":[10,43,53,58,85,88,153],"technologies":[11],"for":[12],"mobile,":[13],"personalised":[14],"speech-tospeech":[15],"translation":[16],"systems.":[17],"hidden":[19],"Markov":[20],"model":[21,125],"being":[23],"used":[24],"as":[25],"underlying":[27],"technology":[28],"both":[30],"automatic":[31],"speech":[32],"recognition":[33],"(ASR)":[34],"and":[35,70,75,83,97,108,113,133],"text-to-speech":[36],"synthesis":[37],"(TTS)":[38],"components,":[39],"thus,":[40],"investigation":[42,152],"unified":[44,155],"statistical":[45,124],"modelling":[46,156],"approaches":[47],"has":[48],"become":[49],"an":[50],"implicit":[51],"goal":[52],"our":[54],"research.":[55],"As":[56],"one":[57],"first":[60],"steps":[61],"towards":[62],"this":[63,78],"goal,":[64],"we":[65,80],"have":[66,91],"been":[67,92],"investigating":[68],"commonalities":[69],"differences":[71],"between":[72],"HMM-based":[73],"ASR":[74,96,132],"TTS.":[76],"In":[77],"paper":[79],"present":[81],"results":[82,118],"analysis":[84],"a":[86,144],"series":[87],"experiments":[89],"that":[90],"conducted":[93],"on":[94],"English":[95],"TTS":[98,134],"systems":[99],"measuring":[100],"their":[101],"performance":[102,135],"with":[103],"respect":[104],"to":[105,147],"phone":[106],"set":[107],"lexicon,":[109],"acoustic":[110],"feature":[111],"type":[112],"dimensionality":[114],"andHMM":[115],"topology.":[116],"Our":[117],"show":[119],"that,":[120],"although":[121],"fundamental":[123],"may":[126],"be":[127,148],"essentially":[128],"same,":[130],"optimal":[131],"often":[136],"demands":[137],"diametrically":[138],"opposed":[139],"system":[140],"designs.":[141],"This":[142],"represents":[143],"major":[145],"challenge":[146],"addressed":[149],"such":[154],"approaches.":[157]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}