{"id":"https://openalex.org/W163616957","doi":"https://doi.org/10.21437/interspeech.2008-189","title":"HMM-based Finnish text-to-speech system utilizing glottal inverse filtering","display_name":"HMM-based Finnish text-to-speech system utilizing glottal inverse filtering","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W163616957","doi":"https://doi.org/10.21437/interspeech.2008-189","mag":"163616957"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-189","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009644866","display_name":"Antti Suni","orcid":"https://orcid.org/0000-0003-3414-6035"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Antti Suni","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076286418","display_name":"Hannu Pulakka","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hannu Pulakka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040474925","display_name":"Martti Vainio","orcid":"https://orcid.org/0000-0003-2570-0196"},"institutions":[{"id":"https://openalex.org/I133731052","display_name":"University of Helsinki","ror":"https://ror.org/040af2s02","country_code":"FI","type":"education","lineage":["https://openalex.org/I133731052"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Martti Vainio","raw_affiliation_strings":["University of Helsinki, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"University of Helsinki, Helsinki, Finland","institution_ids":["https://openalex.org/I133731052"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042186400","display_name":"Paavo Alku","orcid":"https://orcid.org/0000-0002-8173-9418"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paavo Alku","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5000571465"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.2969,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.97939655,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1881","last_page":"1884"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.996399998664856,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7960784435272217},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7887977361679077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7451979517936707},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7142478227615356},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5184778571128845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32097408175468445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1360914409160614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7960784435272217},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7887977361679077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7451979517936707},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7142478227615356},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5184778571128845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32097408175468445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1360914409160614},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2008-189","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W200094172","https://openalex.org/W344150399","https://openalex.org/W1519698338","https://openalex.org/W1536990986","https://openalex.org/W1756939916","https://openalex.org/W1972730872","https://openalex.org/W2021320575","https://openalex.org/W2049083033","https://openalex.org/W2096980176","https://openalex.org/W2108674328","https://openalex.org/W2151225171","https://openalex.org/W2153738419","https://openalex.org/W2286166914"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2904846757"],"abstract_inverted_index":{"Abstract":[0],"This":[1,465],"paper":[2,628],"describes":[3,634],"an":[4,41,516,597],"HMM-based":[5,255,293,361,517,598,608],"speech":[6,23,62,113,133,149,208,311,323,339,414,450,475,518,576,609,621,656],"synthesis":[7,126,340,476,610,657],"sys-tem":[8,611],"that":[9,86,283,501,612],"utilizes":[10,613],"glottal":[11,115,455,469,485,525,549,559,571,593,614],"inverse":[12,33,116,560,594,615],"\ufb01ltering":[13,34,561,595,616],"for":[14,44,145,220,250,287,343,396,617],"generating":[15,93,618],"naturalsounding":[16,94,619],"synthetic":[17,207,413,620],"speech.":[18,357,489],"In":[19,161,233],"the":[20,77,82,87,97,138,177,181,189,195,223,244,269,288,387,410,427,435,440,446,454,461,468,484,493,498,521,556,589,627,635,642,645,654],"proposed":[21,88,482,564,636],"system,":[22],"is\ufb01rst":[24],"parametrized":[25],"into":[26],"spectral":[27],"and":[28,46,69,96,158,193,230,263,477,588,659,666],"excitation":[29,110,399,422],"features":[30],"using":[31,429],"aglottal":[32],"based":[35,199,569],"method.":[36],"The":[37,121,201,624,639],"parameters":[38],"are":[39,63,187,306,577,647,662,669],"fedinto":[40],"HMM":[42,51,118,271,389],"system":[43,89,225,658],"training":[45],"then":[47],"generated":[48,80,459],"from":[49,60,134,260,275,325,434,553,591],"thetrained":[50],"according":[52,75],"to":[53,76,103,129,205,226,341,386,416,535,579],"text":[54],"input.":[55],"Glottal":[56],"\ufb02ow":[57,526,550,572],"pulses":[58,527,551,573],"ex-tracted":[59],"real":[61,441,554],"used":[64,504],"as":[65,321,329,352,354,373,512,514,583,630],"a":[66,106,264,284,418,530,536,606],"voice":[67,327,350,370,443],"source,":[68,470],"thevoice":[70],"source":[71,486],"is":[72,90,99,128,337,451,622],"further":[73],"modi\ufb01ed":[74],"all-pole":[78],"modelparameters":[79],"by":[81,299,394,453,460],"HMM.":[83],"Preliminary":[84],"experimentsshow":[85],"capable":[91],"of":[92,124,209,246,301,316,348,356,412,426,437,448,487,497,523,547,558,585,626,641],"speech,":[95],"quality":[98,411,425,436,533],"clearly":[100],"better":[101,261],"compared":[102,415],"asystem":[104],"utilizing":[105,548],"conventional":[107],"impulse":[108,420],"train":[109,421],"model.Index":[111],"Terms:":[112],"synthesis,":[114],"\ufb01ltering,":[117],"1.":[119],"Introduction":[120],"ultimate":[122],"goal":[123],"text-to-speech":[125],"(TTS)":[127],"enablecreating":[130],"natural":[131,211,310,438,488,575],"sounding":[132],"arbitrary":[135],"text.":[136],"More-over,":[137],"current":[139,270,292],"trend":[140],"in":[141,150,176,252,257,278,506,529,649,671],"TTS":[142,224,248,294],"research":[143],"calls":[144],"systems":[146,295,428],"thatenable":[147],"producing":[148],"different":[151,227,326,349],"speaking":[152,228,376],"styles":[153,229],"with":[154,366,596,644],"dif-ferent":[155],"speaker":[156,231,374],"characteristics":[157,328,351],"even":[159],"emotions.":[160],"order":[162],"toful\ufb01ll":[163],"these":[164,359,430],"stringent":[165],"general":[166],"requirements,":[167],"two":[168,185],"major":[169],"synthe-sis":[170,509],"techniques":[171,216,304,393,405,431,479],"have":[172,363,384,406,480,600],"attracted":[173,473],"increasing":[174],"interest":[175],"speechresearch":[178],"community":[179],"during":[180],"past":[182],"decade.":[183],"These":[184,404],"alter-natives":[186],"(1)":[188],"unit":[190,214],"selection":[191,215],"technique":[192],"(2)":[194],"hiddenMarkov":[196],"model":[197,496],"(HMM)":[198],"approach.":[200],"former":[202],"has":[203,471,502,562],"beenshown":[204],"yield":[206],"highly":[210],"quality.":[212,279],"How-ever,":[213],"do":[217],"not":[218,601],"allow":[219],"easy":[221],"adaptationof":[222],"char-acteristics.":[232],"addition,":[234],"their":[235,331],"implementation":[236],"requires":[237],"databasesof":[238],"extensive":[239],"sizes,":[240],"which":[241,305],"severely":[242],"limit":[243],"use":[245,522],"this":[247,544,604],"tech-nique,":[249],"example,":[251,397],"mobile":[253],"terminals.":[254],"tech-niques,":[256],"turn,":[258],"bene\ufb01t":[259],"adaptability":[262],"clearlysmaller":[265],"memory":[266],"requirement.":[267],"However,":[268,520],"sys-tems":[272],"often":[273],"suffer":[274],"degraded":[276],"naturalness":[277,290],"It":[280],"canbe":[281],"argued":[282],"potential":[285],"reason":[286],"reduced":[289],"inthe":[291],"can":[296,318],"be":[297,319],"explained":[298],"theuse":[300],"signal":[302,391],"generation":[303],"oversimpli\ufb01ed":[307],"toproperly":[308],"mimic":[309],"pressure":[312],"waveforms.A":[313],"large":[314],"part":[315],"what":[317],"characterized":[320],"naturalnessin":[322],"emerges":[324],"wellas":[330],"context":[332],"dependent":[333],"changes.":[334],"Therefore,":[335],"it":[336],"justi\ufb01edin":[338],"search":[342],"methods":[344],"aiming":[345],"at":[346,539],"accuratemodeling":[347],"well":[353,513],"prosodicfeatures":[355],"Towards":[358],"goals,":[360],"synthe-sizers":[362],"been":[364,407,481,503,563,602],"developed":[365],"special":[367,580],"emphasis":[368],"on":[369,570,653],"char-acteristics":[371],"such":[372,491,582],"individualities,":[375],"styles,":[377],"andemotions":[378],"[1].":[379],"Moreover,":[380],"some":[381],"recent":[382],"studies":[383,568],"introducedimprovements":[385],"parametric":[388],"systems\u2019":[390],"genera-tion":[392],"utilizing,":[395],"mixed":[398],"[2]and":[400],"residual":[401],"modeling":[402],"[3].":[403],"shownto":[408],"improve":[409],"systemsutilizing":[417],"traditional":[419,507],"model.":[423],"However,the":[424],"still":[432],"remainsfar":[433],"speech.In":[439],"human":[442],"production":[444],"mechanism,":[445],"excita-tion":[447],"(voiced)":[449],"represented":[452],"volume":[456],"ve-locity":[457],"waveform":[458],"vibrating":[462],"vocal":[463],"folds.":[464],"ex-citation":[466],"signal,":[467],"naturally":[472],"interestin":[474],"many":[478],"tomimic":[483],"One":[490],"techniqueis":[492],"Liljencrants-Fant":[494],"(LF)":[495],"differentiated":[499],"glottalsource":[500],"both":[505],"rule-based":[508],"[4,":[510],"5]":[511],"within":[515],"synthesizer[6].":[519],"arti\ufb01cial":[524],"usuallyresults":[528],"somewhat":[531],"buzzy":[532],"due":[534],"strong":[537],"harmonicstructure":[538],"higher":[540],"frequencies.":[541],"To":[542],"overcome":[543],"problem,":[545],"theidea":[546],"extracted":[552],"speechwith":[555],"help":[557],"[7,":[565],"8].However,":[566],"previous":[567],"extractedfrom":[574],"limited":[578],"purposes":[581],"thegeneration":[584],"isolated":[586],"vowels,":[587],"bene\ufb01ts":[590],"combiningautomatic":[592],"speechsynthesizer":[599],"utilized.In":[603],"paper,":[605],"novel":[607],"presented.":[623],"rest":[625],"isorganized":[629],"follows:":[631],"Section":[632,650,672],"2":[633],"speechsynthesis":[637],"system.":[638],"results":[640],"experiments":[643],"newsynthesizer":[646],"presented":[648,663,670],"3.":[651],"Discussion":[652],"pro-posed":[655],"future":[660],"plans":[661],"inSection":[664],"4,":[665],"\ufb01nal":[667],"conclusions":[668],"5.":[673]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}