{"id":"https://openalex.org/W2170592828","doi":"https://doi.org/10.1109/icassp.2012.6288927","title":"A small footprint hybrid statistical/unit selection text-to-speech synthesis system for agglutinative languages","display_name":"A small footprint hybrid statistical/unit selection text-to-speech synthesis system for agglutinative languages","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2170592828","doi":"https://doi.org/10.1109/icassp.2012.6288927","mag":"2170592828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079295537","display_name":"Ekrem G\u00fcner","orcid":null},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Ekrem Guner","raw_affiliation_strings":["Ozyegin University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016845689","display_name":"Cenk Demiro\u011flu","orcid":"https://orcid.org/0000-0002-6160-3169"},"institutions":[{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Cenk Demiroglu","raw_affiliation_strings":["Ozyegin University, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"Ozyegin University, Istanbul, Turkey","institution_ids":["https://openalex.org/I44925452"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079295537"],"corresponding_institution_ids":["https://openalex.org/I44925452"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.14425619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4537","last_page":"4540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9933000206947327,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9872000217437744,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7894724607467651},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.7247818112373352},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6395487785339355},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5808808207511902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5342620611190796},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4940343499183655},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4891946315765381},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.4753667712211609},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4448506832122803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3349539041519165},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2634196877479553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7894724607467651},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.7247818112373352},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6395487785339355},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5808808207511902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5342620611190796},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4940343499183655},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4891946315765381},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.4753667712211609},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4448506832122803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3349539041519165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2634196877479553},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2012.6288927","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eresearch.ozyegin.edu.tr:10679/674","is_oa":false,"landing_page_url":"http://hdl.handle.net/10679/674","pdf_url":null,"source":{"id":"https://openalex.org/S4306400232","display_name":"ECS Journal of Solid State Science and Technology (The Electrochemical Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2802273670","host_organization_name":"Electrochemical Society","host_organization_lineage":["https://openalex.org/I2802273670"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W14365481","https://openalex.org/W205224898","https://openalex.org/W1564152904","https://openalex.org/W1669179077","https://openalex.org/W1973047048","https://openalex.org/W1990645831","https://openalex.org/W2155433314","https://openalex.org/W2165848216","https://openalex.org/W2394921947","https://openalex.org/W3142087749","https://openalex.org/W4239162268","https://openalex.org/W4285719527","https://openalex.org/W4395962053","https://openalex.org/W6600591330","https://openalex.org/W6608382078","https://openalex.org/W6633741138","https://openalex.org/W6637020583","https://openalex.org/W6712208827","https://openalex.org/W6759256681"],"related_works":["https://openalex.org/W2728343294","https://openalex.org/W4387891631","https://openalex.org/W4387913002","https://openalex.org/W2896235912","https://openalex.org/W3113091479","https://openalex.org/W2162899405","https://openalex.org/W2081919107","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W2811496854"],"abstract_inverted_index":{"Despite":[0],"its":[1],"success,":[2],"unit":[3,54,83],"selection":[4,55,84],"based":[5],"text-to-speech":[6],"synthesis":[7],"(TTS)":[8],"has":[9,10,28],"some":[11],"disadvantages":[12],"such":[13],"as":[14],"sudden":[15],"discontinuities":[16],"in":[17,52,125,139],"speech":[18],"that":[19,49,90],"distract":[20],"the":[21,35,41,44,53,60,64,94,97,103,113,119,126,132,136,140],"listeners.":[22],"The":[23,107],"HMM-based":[24],"TTS":[25,36,85],"(HTS)":[26],"approach":[27],"been":[29],"increasingly":[30],"getting":[31],"more":[32],"attention":[33],"from":[34],"research":[37],"community.":[38],"One":[39],"of":[40,46,59,96,112,122],"advantage":[42,58],"is":[43,63],"lack":[45],"spurious":[47],"errors":[48],"are":[50,116],"observed":[51],"scheme.":[56],"Another":[57],"HTS":[61,99],"system":[62,86,100,115,134,138],"small":[65],"memory":[66,104],"footprint":[67,105],"requirement":[68],"which":[69],"makes":[70],"it":[71],"attractive":[72],"for":[73,87],"embedded":[74],"devices.":[75],"Here,":[76],"we":[77],"propose":[78],"a":[79],"novel":[80],"hybrid":[81,133],"statistical":[82],"agglutinative":[88],"languages":[89],"aims":[91],"at":[92],"improving":[93],"quality":[95,110],"baseline":[98,114,137],"while":[101],"keeping":[102],"small.":[106],"intelligibility":[108],"and":[109],"scores":[111,121],"comparable":[117],"to":[118],"MOS":[120],"English":[123],"reported":[124],"Blizzard":[127],"Challenge":[128],"tests.":[129,143],"Listeners":[130],"preferred":[131],"over":[135],"A/B":[141],"preference":[142]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}
