{"id":"https://openalex.org/W81231479","doi":"https://doi.org/10.21437/interspeech.2010-127","title":"Large vocabulary continuous speech recognition using WFST-based linear classifier for structured data","display_name":"Large vocabulary continuous speech recognition using WFST-based linear classifier for structured data","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W81231479","doi":"https://doi.org/10.21437/interspeech.2010-127","mag":"81231479"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-127","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018620798","display_name":"Atsushi Nakamura","orcid":"https://orcid.org/0000-0003-0788-2221"},"institutions":[{"id":"https://openalex.org/I4210092597","display_name":"NTT (United States)","ror":"https://ror.org/004cn7092","country_code":"US","type":"company","lineage":["https://openalex.org/I2251713219","https://openalex.org/I4210092597"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":["Nippon Telegraph & Telephone"],"affiliations":[{"raw_affiliation_string":"Nippon Telegraph & Telephone","institution_ids":["https://openalex.org/I4210092597"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001291873"],"corresponding_institution_ids":["https://openalex.org/I4210092597"],"apc_list":null,"apc_paid":null,"fwci":4.9615,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.94823923,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"346","last_page":"349"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9977999925613403,"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":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8147542476654053},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7681275010108948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7408869862556458},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6442989706993103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6415388584136963},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6387569308280945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5981485247612},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5958455801010132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5609651207923889},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5607250928878784},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.4450906813144684},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.42027124762535095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2199346125125885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.126804918050766}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8147542476654053},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7681275010108948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408869862556458},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6442989706993103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6415388584136963},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6387569308280945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5981485247612},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5958455801010132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5609651207923889},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5607250928878784},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.4450906813144684},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.42027124762535095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2199346125125885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.126804918050766},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-127","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W43454013","https://openalex.org/W191444391","https://openalex.org/W1984196678","https://openalex.org/W1984906370","https://openalex.org/W2046932483","https://openalex.org/W2131033001","https://openalex.org/W2138302120","https://openalex.org/W2138889249","https://openalex.org/W2150907703","https://openalex.org/W2154075111","https://openalex.org/W2156615793","https://openalex.org/W2158148237","https://openalex.org/W2169384404","https://openalex.org/W2336725036"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W161037869","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2162550210","https://openalex.org/W2098198482"],"abstract_inverted_index":{"This":[0,106],"paper":[1,107],"describes":[2],"a":[3,30,53,90,100,109,113,123,139],"discriminative":[4,160],"approach":[5,20,67,134],"that":[6,69,131],"further":[7],"advances":[8],"the":[9,27,48,66,70,75,85,132,152,155],"framework":[10],"for":[11,25,56,112],"Weighted":[12],"Finite":[13],"State":[14],"Transducer":[15],"(WFST)":[16],"based":[17,159],"decoding.":[18],"The":[19,63,127],"introduces":[21],"additional":[22,76],"linear":[23,54,77,115,173],"models":[24,38,42,78],"adjusting":[26],"scores":[28],"of":[29,34,72,74,87,154,162],"decoding":[31,50,120],"graph":[32],"composed":[33],"conventional":[35],"information":[36],"source":[37],"(e.g.,":[39,59],"hidden":[40],"Markov":[41],"and":[43,46,92,146],"N-gram":[44],"models),":[45],"reviews":[47],"WFSTbased":[49,119],"process":[51],"as":[52],"classifier":[55,116],"structured":[57],"data":[58],"sequential":[60],"multiclass":[61],"data).":[62],"difficulty":[64],"with":[65,151],"is":[68],"number":[71,86],"dimensions":[73],"becomes":[79],"very":[80],"large":[81,140,177],"in":[82,89,118],"proportion":[83],"to":[84,99,138],"arcs":[88],"WFST,":[91],"our":[93],"previous":[94],"study":[95],"only":[96],"applied":[97,137],"it":[98],"small":[101],"task":[102],"(TIMIT":[103],"phoneme":[104],"recognition).":[105],"proposes":[108],"training":[110,161],"method":[111],"large-scale":[114],"employed":[117],"by":[121],"using":[122],"distributed":[124,175],"perceptron":[125],"algorithm.":[126],"experimental":[128],"results":[129],"show":[130],"proposed":[133],"was":[135],"successfully":[136],"vocabulary":[141,178],"continuous":[142,179],"speech":[143,167,180],"recognition":[144,181],"task,":[145],"achieved":[147],"an":[148],"improvement":[149],"compared":[150],"performance":[153],"minimum":[156],"phone":[157],"error":[158],"acoustic":[163],"models.":[164],"Index":[165],"Terms:":[166],"recognition,":[168],"weighted":[169],"finite":[170],"state":[171],"transducer,":[172],"classifier,":[174],"perceptron,":[176]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}