{"id":"https://openalex.org/W2408532390","doi":"https://doi.org/10.21437/interspeech.2013-467","title":"Discriminative training of WFST factors with application to pronunciation modeling","display_name":"Discriminative training of WFST factors with application to pronunciation modeling","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2408532390","doi":"https://doi.org/10.21437/interspeech.2013-467","mag":"2408532390"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-467","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5036738038","display_name":"Preethi Jyothi","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Preethi Jyothi","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056667180","display_name":"Eric Fosler\u2010Lussier","orcid":"https://orcid.org/0000-0001-8004-5169"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Fosler-Lussier","raw_affiliation_strings":["Ohio State University"],"affiliations":[{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015602781","display_name":"Karen Livescu","orcid":"https://orcid.org/0000-0003-4962-946X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karen Livescu","raw_affiliation_strings":["Toyota Technological Institute at Chicago,"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago,","institution_ids":["https://openalex.org/I160992636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036738038"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.4827,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.8737262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1961","last_page":"1965"},"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/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8510656356811523},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.8429195880889893},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8296869993209839},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.7406320571899414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5500685572624207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5371004343032837},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4890216290950775},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.48603183031082153},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44951462745666504},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4467525780200958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4039934277534485}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8510656356811523},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.8429195880889893},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8296869993209839},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.7406320571899414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5500685572624207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5371004343032837},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4890216290950775},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.48603183031082153},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44951462745666504},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4467525780200958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4039934277534485},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-467","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.411.7494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.411.7494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ttic.uchicago.edu/~klivescu/papers/jyothi_interspeech2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W13802415","https://openalex.org/W81231479","https://openalex.org/W191444391","https://openalex.org/W196692374","https://openalex.org/W1495239264","https://openalex.org/W1524333225","https://openalex.org/W1582482241","https://openalex.org/W1583757088","https://openalex.org/W1764939238","https://openalex.org/W2046932483","https://openalex.org/W2127611282","https://openalex.org/W2132991150","https://openalex.org/W2134861448","https://openalex.org/W2138889249","https://openalex.org/W2139406248","https://openalex.org/W2154075111","https://openalex.org/W2158148237","https://openalex.org/W2160218441","https://openalex.org/W2166637769","https://openalex.org/W2166765763","https://openalex.org/W2295531324","https://openalex.org/W2395951356","https://openalex.org/W2399021751","https://openalex.org/W2402972567"],"related_works":["https://openalex.org/W2153719181","https://openalex.org/W2183593636","https://openalex.org/W1971748923","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W1566155057","https://openalex.org/W2060986072"],"abstract_inverted_index":{"One":[0],"of":[1,9,58,91,99],"the":[2,13,80,102,149],"most":[3],"popular":[4],"speech":[5],"recognition":[6,137,146],"architectures":[7],"consists":[8],"multiple":[10],"components":[11],"(like":[12],"acoustic,":[14],"pronunciation":[15,134],"and":[16,40],"language":[17],"models)":[18],"that":[19],"are":[20,35],"modeled":[21],"as":[22],"weighted":[23,156],"finite":[24,157],"state":[25,158],"transducer":[26],"(WFST)":[27],"factors":[28],"in":[29,38,71,124,142,145],"a":[30,92,125,133],"cascade.":[31,82,126],"These":[32],"factor":[33,69,93,103],"WFSTs":[34,70,123],"typically":[36],"trained":[37],"isolation":[39],"combined":[41],"efficiently":[42],"for":[43,52,113,117,136],"decoding.":[44],"Recent":[45],"work":[46],"has":[47],"explored":[48],"jointly":[49],"estimating":[50],"parameters":[51,90],"these":[53],"models":[54,115],"using":[55,95],"considerable":[56],"amounts":[57,98],"training":[59,111,119],"data.":[60],"We":[61,127],"propose":[62],"an":[63,73,109],"alternative":[64],"approach":[65,107],"to":[66,87,131],"selectively":[67],"train":[68,132],"such":[72],"architecture,":[74],"while":[75],"still":[76],"leveraging":[77],"information":[78],"from":[79],"entire":[81],"This":[83],"technique":[84],"allows":[85],"us":[86],"effectively":[88],"estimate":[89],"WFST":[94],"relatively":[96],"small":[97],"data,":[100],"if":[101],"is":[104],"small.":[105],"Our":[106],"involves":[108],"online":[110],"paradigm":[112],"linear":[114],"adapted":[116],"discriminatively":[118],"one":[120],"or":[121],"more":[122],"apply":[128],"this":[129],"method":[130],"model":[135],"on":[138],"conversational":[139],"speech,":[140],"resulting":[141],"significant":[143],"improvements":[144],"performance":[147],"over":[148],"baseline":[150],"model.":[151],"Index":[152],"Terms:":[153],"Pronunciation":[154],"models,":[155],"transducers,":[159],"large-margin":[160],"training.":[161]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}