{"id":"https://openalex.org/W2534278972","doi":"https://doi.org/10.1109/coginfocom.2012.6421951","title":"Characteristics and spectral features used in automatic prediction of vowel duration in spontaneous speech","display_name":"Characteristics and spectral features used in automatic prediction of vowel duration in spontaneous speech","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2534278972","doi":"https://doi.org/10.1109/coginfocom.2012.6421951","mag":"2534278972"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2012.6421951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2012.6421951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)","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/A5032873613","display_name":"Andr\u00e1s Beke","orcid":null},"institutions":[{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]},{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"A. Beke","raw_affiliation_strings":["MTA Research Institute for Linguistics, Phonetics, Hungarian Academy of Sciences, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"MTA Research Institute for Linguistics, Phonetics, Hungarian Academy of Sciences, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I7597260"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024426827","display_name":"M\u00e1ria G\u00f3sy","orcid":"https://orcid.org/0000-0003-4336-3007"},"institutions":[{"id":"https://openalex.org/I7597260","display_name":"Hungarian Academy of Sciences","ror":"https://ror.org/02ks8qq67","country_code":"HU","type":"government","lineage":["https://openalex.org/I7597260"]},{"id":"https://openalex.org/I2802350943","display_name":"ELTE Hungarian Research Centre for Linguistics","ror":"https://ror.org/005cqsz63","country_code":"HU","type":"facility","lineage":["https://openalex.org/I2802350943"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"M. Gosy","raw_affiliation_strings":["MTA Research Institute for Linguistics, Phonetics, Hungarian Academy of Sciences, Budapest, Hungary"],"affiliations":[{"raw_affiliation_string":"MTA Research Institute for Linguistics, Phonetics, Hungarian Academy of Sciences, Budapest, Hungary","institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I7597260"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032873613"],"corresponding_institution_ids":["https://openalex.org/I2802350943","https://openalex.org/I7597260"],"apc_list":null,"apc_paid":null,"fwci":0.8563,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81239912,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"65","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/vowel","display_name":"Vowel","score":0.8500738143920898},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7267164587974548},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6776077747344971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6271772980690002},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5713996887207031},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44432151317596436},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.4402828812599182},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37152087688446045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3656628429889679},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1079842746257782}],"concepts":[{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.8500738143920898},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7267164587974548},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6776077747344971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6271772980690002},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5713996887207031},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44432151317596436},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.4402828812599182},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37152087688446045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3656628429889679},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1079842746257782},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coginfocom.2012.6421951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2012.6421951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W38355094","https://openalex.org/W42404803","https://openalex.org/W133766486","https://openalex.org/W148091393","https://openalex.org/W182568096","https://openalex.org/W604781219","https://openalex.org/W1481289821","https://openalex.org/W1534316483","https://openalex.org/W1537117028","https://openalex.org/W1555165019","https://openalex.org/W1594031697","https://openalex.org/W1601959396","https://openalex.org/W1603808762","https://openalex.org/W1825819404","https://openalex.org/W1984749204","https://openalex.org/W1989775252","https://openalex.org/W1993533823","https://openalex.org/W2019960027","https://openalex.org/W2049274497","https://openalex.org/W2075170185","https://openalex.org/W2077112835","https://openalex.org/W2092643612","https://openalex.org/W2095089846","https://openalex.org/W2121299803","https://openalex.org/W2127886292","https://openalex.org/W2140939391","https://openalex.org/W2152024332","https://openalex.org/W2152559190","https://openalex.org/W2155884706","https://openalex.org/W2404789019","https://openalex.org/W2766039569","https://openalex.org/W2985376554","https://openalex.org/W3085162807","https://openalex.org/W3216401400","https://openalex.org/W4285719527","https://openalex.org/W4390911882","https://openalex.org/W6601558908","https://openalex.org/W6601742036","https://openalex.org/W6605514845","https://openalex.org/W6631909717","https://openalex.org/W6631973195","https://openalex.org/W6638708641","https://openalex.org/W6662737280","https://openalex.org/W6713478506","https://openalex.org/W6770054888","https://openalex.org/W6860749638"],"related_works":["https://openalex.org/W1995619422","https://openalex.org/W4390926392","https://openalex.org/W2940658159","https://openalex.org/W2741358513","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000"],"abstract_inverted_index":{"Many":[0],"phonetic":[1,52],"and":[2,12,95,101,130,167,195,223,276],"phonology":[3],"domain":[4],"research":[5],"papers":[6],"analyzed":[7],"segmental":[8,261],"duration:":[9],"what":[10],"factors":[11,15,49],"interactions":[13],"between":[14,165,192,220],"determine":[16],"their":[17],"duration.":[18,111],"Their":[19],"results":[20,186,214,235],"often":[21],"play":[22],"an":[23],"important":[24],"role":[25],"in":[26,41,58,62,75,144],"Language":[27],"Technology":[28],"applications,":[29],"for":[30,237,271],"example":[31],"TTS":[32],"(text-to-speech":[33],"synthesis),":[34],"ASR":[35],"(automatic":[36],"speech":[37,65,77,153],"recognition)":[38],"widely":[39],"used":[40,107,119,212],"infocommunication.":[42],"Speech":[43],"sound":[44],"duration":[45,74,123,198,226],"depends":[46],"on":[47,79,247,252],"various":[48],"such":[50],"as":[51,142,266],"quality,":[53],"phonological":[54,56],"context,":[55],"position":[57],"the":[59,63,92,114,125,185,190,193,208,213,218,221,240,248,253,257],"word":[60],"or":[61],"utterance,":[64],"style,":[66],"etc.":[67],"We":[68],"intended":[69],"to":[70,108,120],"automatically":[71],"predict":[72,121],"vowel":[73,93,110,122,140,169,197,225,245],"spontaneous":[76,152,264],"based":[78],"three":[80],"methods.":[81],"(i)":[82],"A":[83],"classification/regression":[84],"tree":[85],"(CART)":[86],"using":[87,124,183],"some":[88],"characteristic":[89,128],"features":[90,100,129,210,243],"of":[91,127,148,178,242,260,263],"quality":[94],"context.":[96],"(ii)":[97],"The":[98,234],"same":[99],"feedforward":[102],"neural":[103],"network":[104],"(FFNN)":[105],"were":[106,136,187,211,215],"model":[109],"(iii)":[112],"In":[113],"third":[115],"method":[116],"FFNN":[117,184],"was":[118,160,199,203,227,231],"combination":[126],"spectral":[131],"features.":[132],"Empirical":[133],"durational":[134],"data":[135,154],"obtained":[137,236],"by":[138],"measuring":[139],"durations":[141],"attested":[143],"over":[145],"110":[146],"minutes":[147],"a":[149,161],"large":[150],"Hungarian":[151,238],"base":[155],"(BEA).":[156],"Using":[157],"CART":[158],"there":[159],"poor":[162],"correlation":[163,191,219],"(0.57)":[164],"measured":[166],"predicted":[168,196,224],"duration,":[170,246],"with":[171],"average":[172],"RMSE":[173,202,230],"(root":[174],"mean":[175],"square":[176],"error)":[177],"approximately":[179],"33":[180],"ms.":[181,206,233],"When":[182,207],"slightly":[188],"better:":[189,217],"target":[194,222],"0.62":[200],"while":[201,229,251],"about":[204],"29":[205],"combined":[209],"even":[216],"0.79":[228],"25":[232],"support":[239],"complexity":[241,259],"affecting":[244],"one":[249],"hand,":[250],"other":[254],"they":[255],"indicate":[256],"temporal":[258],"level":[262],"speech,":[265],"has":[267],"already":[268],"been":[269],"reported":[270],"Lithuanian,":[272],"Czech,":[273],"Hindi,":[274],"Telugu":[275],"Korean.":[277]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
