{"id":"https://openalex.org/W586333776","doi":null,"title":"Semi-supervised learning for acoustic and prosodic modeling in speech applications","display_name":"Semi-supervised learning for acoustic and prosodic modeling in speech applications","publication_year":2012,"publication_date":"2012-06-27","ids":{"openalex":"https://openalex.org/W586333776","mag":"586333776"},"language":"en","primary_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/32006","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/32006","pdf_url":"https://www.ideals.illinois.edu/items/32271/bitstreams/105811/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ideals.illinois.edu/items/32271/bitstreams/105811/data.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113439913","display_name":"Jui Ting Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jui Ting Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5113439913"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5804,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69899087,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.0003000000142492354,"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":0.0,"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/semi-supervised-learning","display_name":"semi-supervised learning","score":1.0},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.8410000205039978},{"id":"https://openalex.org/keywords/prosodic-modeling","display_name":"prosodic modeling","score":0.8700000047683716},{"id":"https://openalex.org/keywords/phone-classification","display_name":"phone classification","score":0.7350000143051147},{"id":"https://openalex.org/keywords/phone-recognition","display_name":"phone recognition","score":0.984000027179718},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.7540000081062317},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/continuous-density-hmm","display_name":"continuous density HMM","score":0.7829999923706055},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7350000143051147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6021696329116821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6014465689659119},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.385235995054245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3800106644630432}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:www.ideals.illinois.edu:2142/32006","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/32006","pdf_url":"https://www.ideals.illinois.edu/items/32271/bitstreams/105811/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.4704","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.4704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2012/huang12thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.981.2166","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.981.2166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.ideals.illinois.edu/bitstream/handle/2142/32006/Huang_JuiTing.pdf?sequence%3D1","raw_type":"text"},{"id":"mag:586333776","doi":null,"is_oa":false,"landing_page_url":"https://www.ideals.illinois.edu/handle/2142/32006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:www.ideals.illinois.edu:2142/32006","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2142/32006","pdf_url":"https://www.ideals.illinois.edu/items/32271/bitstreams/105811/data.pdf","source":{"id":"https://openalex.org/S4306401358","display_name":"Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801919071","host_organization_name":"University of Illinois System","host_organization_lineage":["https://openalex.org/I2801919071"],"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":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W586333776.pdf","grobid_xml":"https://content.openalex.org/works/W586333776.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W28194048","https://openalex.org/W30596880","https://openalex.org/W51742649","https://openalex.org/W57361413","https://openalex.org/W130324013","https://openalex.org/W131252740","https://openalex.org/W137179480","https://openalex.org/W162654330","https://openalex.org/W176510440","https://openalex.org/W206571999","https://openalex.org/W1479807131","https://openalex.org/W1539023901","https://openalex.org/W1550374377","https://openalex.org/W1554457642","https://openalex.org/W1586176709","https://openalex.org/W1589170661","https://openalex.org/W1631260214","https://openalex.org/W1635512741","https://openalex.org/W1646405990","https://openalex.org/W1665196592","https://openalex.org/W1877570817","https://openalex.org/W1932968309","https://openalex.org/W1975113979","https://openalex.org/W1978671188","https://openalex.org/W1979679014","https://openalex.org/W1993347555","https://openalex.org/W2002342963","https://openalex.org/W2033178790","https://openalex.org/W2048679005","https://openalex.org/W2049633694","https://openalex.org/W2049950192","https://openalex.org/W2056133372","https://openalex.org/W2056786202","https://openalex.org/W2077574412","https://openalex.org/W2077804127","https://openalex.org/W2088965663","https://openalex.org/W2090861223","https://openalex.org/W2096938374","https://openalex.org/W2096991417","https://openalex.org/W2097089247","https://openalex.org/W2097635532","https://openalex.org/W2098318492","https://openalex.org/W2098841537","https://openalex.org/W2100969003","https://openalex.org/W2101694857","https://openalex.org/W2104290444","https://openalex.org/W2104755048","https://openalex.org/W2104997912","https://openalex.org/W2107008379","https://openalex.org/W2110332474","https://openalex.org/W2126940615","https://openalex.org/W2131646590","https://openalex.org/W2132870739","https://openalex.org/W2137054688","https://openalex.org/W2137692354","https://openalex.org/W2139698650","https://openalex.org/W2142416747","https://openalex.org/W2145494108","https://openalex.org/W2146423738","https://openalex.org/W2146871184","https://openalex.org/W2148029428","https://openalex.org/W2148154194","https://openalex.org/W2150969560","https://openalex.org/W2154455818","https://openalex.org/W2154481420","https://openalex.org/W2157590573","https://openalex.org/W2158339352","https://openalex.org/W2159372275","https://openalex.org/W2166317648","https://openalex.org/W2166820052","https://openalex.org/W2168171912","https://openalex.org/W2170461116","https://openalex.org/W2170979168","https://openalex.org/W2171850596","https://openalex.org/W2254292464","https://openalex.org/W2403419258","https://openalex.org/W2426479676","https://openalex.org/W2619993508","https://openalex.org/W2798766386","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W7100752531","https://openalex.org/W2528306949","https://openalex.org/W2189391786","https://openalex.org/W7099656198","https://openalex.org/W2101436878","https://openalex.org/W2007851337","https://openalex.org/W176510440","https://openalex.org/W2757507876","https://openalex.org/W4390926482","https://openalex.org/W3017144692"],"abstract_inverted_index":{"Enormous":[0],"amounts":[1],"of":[2,5,31,45,58,76,102,109,116,132,148,168,177,185,209,252,263,320,332,354,382,393],"audio":[3],"recordings":[4],"human":[6],"speech":[7,18,23,33,142,285],"are":[8,35,127,171,204,388],"essential":[9],"ingredients":[10],"for":[11,16,73,206,275,288,329,366,402],"building":[12,367],"reliable":[13],"statistical":[14],"models":[15,59,131],"many":[17],"applications,":[19],"such":[20],"as":[21,196],"automatic":[22,26,333,369],"recognition":[24,80,95,143,243,290],"and":[25,81,121,158,165,173,212,283,356,397],"prosody":[27,82],"detection.":[28,83,336,406],"However,":[29],"most":[30],"these":[32,210,218],"data":[34,53,160,195,265,306,328,387],"not":[36],"being":[37],"utilized":[38],"because":[39,255],"they":[40],"lack":[41],"transcriptions.":[42],"The":[43,84],"goal":[44],"this":[46,178],"thesis":[47,179],"is":[48,97,161,180,247,257,339],"to":[49,54,181,198,240,325,342],"use":[50,228,262],"untranscribed":[51,284],"(unlabeled)":[52],"improve":[55],"the":[56,74,92,100,106,110,128,183,199,207,235,241,250,261,267,276,317,321,330,351,363,376,380,394,399],"performance":[57,96],"trained":[60],"using":[61,190,304],"only":[62,229,391],"transcribed":[63,103,282],"(labeled)":[64],"data.":[65,104,231],"We":[66,232,271,373],"propose":[67,324],"a":[68,136,146,293],"unified":[69],"semi-supervised":[70,114,149,237,253,313],"learning":[71,254,400],"framework":[72],"problem":[75,246],"phone":[77,79,213,242,289],"classification,":[78],"proposed":[85,236],"approach":[86],"will":[87],"be":[88],"particularly":[89],"useful":[90],"in":[91,135,249,266],"case":[93],"where":[94],"limited":[98],"by":[99,189,299],"amount":[101],"In":[105,316],"first":[107],"part":[108,319],"thesis,":[111,322],"we":[112,323,359],"investigate":[113],"training":[115,150,169,187,201,238,314],"Gaussian":[117],"Mixtures":[118],"Models":[119,124],"(GMMs)":[120],"Hidden":[122],"Markov":[123],"(HMMs)":[125],"which":[126],"common":[129],"probabilistic":[130],"acoustic":[133],"features":[134],"state-of-the-art":[137],"continuous":[138],"density":[139],"HMM":[140],"based":[141],"system.":[144],"Specifically,":[145],"family":[147],"criteria":[151,170,188,219,239],"that":[152,217,227,279,292,375],"reflects":[153],"reasonable":[154],"assumptions":[155],"about":[156],"labeled":[157,230,386],"unlabeled":[159,194,264,305,327],"proposed.":[162],"Both":[163],"generative":[164],"discriminative":[166,186],"kinds":[167],"explored,":[172],"one":[174,392],"important":[175],"proposal":[176],"keep":[182],"power":[184],"some":[191],"measures":[192],"on":[193,260],"regularization":[197],"supervised":[200,225],"objective.":[202],"Methods":[203],"described":[205],"optimization":[208,278],"criteria,":[211],"classification":[214],"experiments":[215],"show":[216,291,374],"reliably":[220,307],"give":[221],"improvements":[222],"over":[223],"their":[224],"versions":[226],"then":[233],"extend":[234],"problem.":[244],"This":[245],"novel":[248],"area":[251],"there":[256],"little":[258],"research":[259],"sequence":[268],"labeling":[269],"problems.":[270],"develop":[272,398],"lattice-based":[273],"approaches":[274],"model":[277,378],"involves":[280],"both":[281],"utterances.":[286],"Experiments":[287],"maximum":[294],"mutual":[295],"information":[296],"criterion":[297],"regularized":[298],"negative":[300],"conditional":[301],"entropy":[302],"measured":[303],"gives":[308],"better":[309],"results":[310],"than":[311,344],"other":[312],"methods.":[315],"second":[318],"exploit":[326],"task":[331],"prosodic":[334,370,404],"event":[335,371],"Prosody":[337],"annotation":[338,364],"even":[340],"harder":[341],"obtain":[343],"orthographic":[345],"text":[346],"transcription;":[347],"it":[348],"usually":[349],"requires":[350],"expert":[352],"knowledge":[353],"phonetics":[355],"linguistics.":[357],"Therefore,":[358],"aim":[360],"at":[361],"reducing":[362],"efforts":[365],"an":[368],"detector.":[372],"mixture":[377],"has":[379],"ability":[381],"class":[383],"discovery":[384],"when":[385],"available":[389],"from":[390],"two":[395],"classes":[396],"algorithm":[401],"unsupervised":[403],"boundary":[405]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}