{"id":"https://openalex.org/W2136237114","doi":"https://doi.org/10.21437/interspeech.2010-602","title":"Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners","display_name":"Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2136237114","doi":"https://doi.org/10.21437/interspeech.2010-602","mag":"2136237114"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-602","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1842/4542","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088212404","display_name":"Michael Pucher","orcid":"https://orcid.org/0000-0002-5374-1342"},"institutions":[{"id":"https://openalex.org/I169108374","display_name":"University of the Basque Country","ror":"https://ror.org/000xsnr85","country_code":"ES","type":"education","lineage":["https://openalex.org/I169108374"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Michael Pucher","raw_affiliation_strings":["University of the Basque Country, Leioa, Spain"],"affiliations":[{"raw_affiliation_string":"University of the Basque Country, Leioa, Spain","institution_ids":["https://openalex.org/I169108374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021462938","display_name":"Dietmar Schabus","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":"Dietmar Schabus","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":"last","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"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088212404"],"corresponding_institution_ids":["https://openalex.org/I169108374"],"apc_list":null,"apc_paid":null,"fwci":0.9326,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81920716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2186","last_page":"2189"},"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":0.9995999932289124,"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":0.9927999973297119,"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":0.7675382494926453},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7601858377456665},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.704725444316864},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.6837899684906006},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6745430827140808},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6216633915901184},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6027141809463501},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5174453854560852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2883915603160858},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25130605697631836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20351174473762512},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1266631782054901}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7675382494926453},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7601858377456665},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.704725444316864},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.6837899684906006},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6745430827140808},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6216633915901184},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6027141809463501},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5174453854560852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2883915603160858},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25130605697631836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20351174473762512},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1266631782054901},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2010-602","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/4542","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4542","pdf_url":"http://hdl.handle.net/1842/4542","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/d81bbfbb-e78a-4e33-8f66-9f2445cbbe9e","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/d81bbfbb-e78a-4e33-8f66-9f2445cbbe9e","pdf_url":"https://www.pure.ed.ac.uk/ws/files/15101403/Synthesis_of_fast_speech_with_interpolation_of_adapted_HSMMs.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:10.1.1.185.695","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.695","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/2010/IS100294.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.4543","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.4543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://userver.ftw.at/~pucher/papers/2010_pucher_synthesis-of-fast-speech_is2010.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d81bbfbb-e78a-4e33-8f66-9f2445cbbe9e","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d81bbfbb-e78a-4e33-8f66-9f2445cbbe9e","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":"Pucher, M, Schabus, D & Yamagishi, J 2010, Synthesis of fast speech with interpolation of adapted HSMMs and its evaluation by blind and sighted listeners. in Proc. Interspeech. pp. 2186-2189.","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/4542","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/4542","pdf_url":"http://hdl.handle.net/1842/4542","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","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8930459011","display_name":null,"funder_award_id":"EC FP7","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320321003","display_name":"Vienna Science and Technology Fund","ror":"https://ror.org/01f9mc681"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2136237114.pdf","grobid_xml":"https://content.openalex.org/works/W2136237114.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1534452177","https://openalex.org/W1599681080","https://openalex.org/W2036233992","https://openalex.org/W2076618452","https://openalex.org/W2098592053","https://openalex.org/W2106792148","https://openalex.org/W2117418893"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2081919107","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854"],"abstract_inverted_index":{"In":[0],"this":[1,71],"paper":[2],"we":[3,59],"evaluate":[4,81],"a":[5,62],"method":[6,72],"for":[7,115,122],"generating":[8],"synthetic":[9],"speech":[10,26,117,127],"at":[11,29],"high":[12],"speaking":[13,33,51],"rates":[14],"based":[15],"on":[16,25],"the":[17,85,89,105],"interpolation":[18,86],"of":[19,87,104,110],"hidden":[20,131],"semi-Markov":[21,132],"models":[22],"(HSMMs)":[23],"trained":[24],"data":[27],"recorded":[28],"normal":[30],"and":[31,53,66,99],"fast":[32,50,116,129],"rates.":[34],"The":[35],"subjective":[36],"evaluation":[37],"was":[38],"carried":[39],"out":[40],"with":[41,70,84],"both":[42],"blind":[43],"listeners,":[44],"who":[45],"are":[46],"used":[47],"to":[48,74],"very":[49],"rates,":[52],"sighted":[54],"listeners.":[55],"We":[56,79],"show":[57],"that":[58],"can":[60],"achieve":[61],"better":[63],"intelligibility":[64],"rate":[65],"higher":[67],"voice":[68],"quality":[69],"compared":[73],"standard":[75,111],"HSMM-based":[76,112],"duration":[77,82,95,113,123],"modeling.":[78,124],"also":[80,97],"modeling":[83,114],"all":[88],"acoustic":[90],"features":[91],"including":[92],"not":[93],"only":[94],"but":[96],"spectral":[98],"F0":[100],"models.":[101],"An":[102],"analysis":[103],"mean":[106],"squared":[107],"error":[108],"(MSE)":[109],"identifies":[118],"problematic":[119],"linguistic":[120],"contexts":[121],"Index":[125],"Terms:":[126],"synthesis,":[128],"speech,":[130],"model":[133]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
