{"id":"https://openalex.org/W2134861448","doi":"https://doi.org/10.1109/tasl.2010.2090518","title":"Learning a Discriminative Weighted Finite-State Transducer for Speech Recognition","display_name":"Learning a Discriminative Weighted Finite-State Transducer for Speech Recognition","publication_year":2010,"publication_date":"2010-12-23","ids":{"openalex":"https://openalex.org/W2134861448","doi":"https://doi.org/10.1109/tasl.2010.2090518","mag":"2134861448"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2090518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2090518","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5007425606","display_name":"Maider Lehr","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maider Lehr","raw_affiliation_strings":["Spoken Language Understanding, Oregon Health and Science University","Center for Spoken Language Understanding, Oregon Health & Science University, Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Spoken Language Understanding, Oregon Health and Science University","institution_ids":["https://openalex.org/I165690674"]},{"raw_affiliation_string":"Center for Spoken Language Understanding, Oregon Health & Science University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null},"institutions":[{"id":"https://openalex.org/I165690674","display_name":"Oregon Health & Science University","ror":"https://ror.org/009avj582","country_code":"US","type":"education","lineage":["https://openalex.org/I165690674"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Izhak Shafran","raw_affiliation_strings":["OHSU","Center for Spoken Language Understanding, Oregon Health & Science University, Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OHSU","institution_ids":[]},{"raw_affiliation_string":"Center for Spoken Language Understanding, Oregon Health & Science University, Portland, OR, USA","institution_ids":["https://openalex.org/I165690674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165690674"],"apc_list":null,"apc_paid":null,"fwci":6.8614,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.96509545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"5","first_page":"1360","last_page":"1367"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9972000122070312,"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/discriminative-model","display_name":"Discriminative model","score":0.8141422867774963},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6809185743331909},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6662251949310303},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6388436555862427},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6252812147140503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6017078161239624},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5152035355567932},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49524322152137756},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46186691522598267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42666614055633545},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.362379789352417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35876214504241943},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21169090270996094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10142621397972107},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09237238764762878}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8141422867774963},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809185743331909},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6662251949310303},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6388436555862427},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6252812147140503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6017078161239624},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5152035355567932},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49524322152137756},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46186691522598267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42666614055633545},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.362379789352417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35876214504241943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21169090270996094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10142621397972107},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09237238764762878},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2010.2090518","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2090518","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.1378","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.1378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cslu.ogi.edu/~zak/is-tasl11.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W153444084","https://openalex.org/W191444391","https://openalex.org/W1997346563","https://openalex.org/W2031287088","https://openalex.org/W2033565080","https://openalex.org/W2046932483","https://openalex.org/W2102294561","https://openalex.org/W2103237065","https://openalex.org/W2106404689","https://openalex.org/W2127217706","https://openalex.org/W2131964822","https://openalex.org/W2132780103","https://openalex.org/W2136727248","https://openalex.org/W2150907703","https://openalex.org/W2154075111","https://openalex.org/W2158025800","https://openalex.org/W2158297186","https://openalex.org/W2158420521","https://openalex.org/W2166339243","https://openalex.org/W2293299267","https://openalex.org/W3149335959","https://openalex.org/W6606255316","https://openalex.org/W6649695541","https://openalex.org/W6684639509"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2529301793","https://openalex.org/W2350724007","https://openalex.org/W2384121599","https://openalex.org/W2355751417","https://openalex.org/W2000075989","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2038083449","https://openalex.org/W2162582511"],"abstract_inverted_index":{"Weighted":[0],"finite-state":[1,101],"transducers":[2,55],"(WFSTs)":[3],"have":[4],"been":[5],"widely":[6],"adopted":[7],"as":[8,108,220],"efficient":[9],"representations":[10],"of":[11,53,117,152,158,203],"a":[12,60,90,133,150,156,183,204],"general":[13,209],"speech":[14,20,186,194],"recognition":[15,187],"model.":[16],"The":[17,69,93],"WFST":[18],"for":[19,199],"recognizer":[21],"is":[22,207],"typically":[23],"assembled":[24],"or":[25],"composed":[26],"from":[27,164],"the":[28,33,37,51,64,67,72,79,111,114,118,141,162,196,201],"several":[29],"components-the":[30],"language":[31,171],"model,":[32],"pronunciation":[34],"mapping":[35],"and":[36,81,113,165,170,212],"acoustic":[38],"model-which":[39],"are":[40,74,87],"estimated":[41],"separately":[42],"without":[43],"any":[44],"end-to-end":[45],"optimization.":[46],"This":[47,121],"paper":[48,191],"examines":[49],"how":[50],"weights":[52,86,202],"such":[54,219],"can":[56,105,213],"be":[57,106,127,214],"learned":[58,88],"in":[59,71,182,210],"manner":[61],"that":[62,140,175],"captures":[63],"interaction":[65],"between":[66,167],"components.":[68],"paths":[70],"transducer":[73,206],"represented":[75],"asn-grams":[76],"defined":[77],"over":[78],"input":[80,112],"output":[82,115],"sequences":[83],"whose":[84],"linear":[85,95],"using":[89],"discriminative":[91],"criterion.":[92],"resulting":[94],"model":[96,143],"factors":[97],"into":[98],"two":[99],"weighted":[100],"acceptors":[102],"(WFSAs)":[103],"which":[104],"applied":[107,215],"corrections":[109],"to":[110,126,173,216],"side":[116],"initial":[119],"WFST.":[120],"formulation":[122],"allows":[123],"duration":[124,176],"cues":[125,177],"incorporated":[128],"seamlessly.":[129],"Empirical":[130],"results":[131],"on":[132,193],"large":[134],"vocabulary":[135],"Arabic":[136,185],"GALE":[137],"task":[138],"demonstrate":[139],"proposed":[142,197],"improves":[144],"word":[145],"error":[146],"rate":[147],"substantially,":[148],"with":[149],"gain":[151],"1.5%-1.7%":[153],"absolute.":[154],"Through":[155],"series":[157],"experiments,":[159],"we":[160],"analyze":[161],"contributions":[163],"interactions":[166],"acoustic,":[168],"duration,":[169],"components":[172],"find":[174],"play":[178],"an":[179],"important":[180],"role":[181],"large-vocabulary":[184],"task.":[188],"Although":[189],"this":[190],"focuses":[192],"recognition,":[195],"framework":[198],"learning":[200],"finite":[205],"more":[208],"nature":[211],"other":[217],"tasks":[218],"utterance":[221],"classification.":[222]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":8}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}