{"id":"https://openalex.org/W1984906370","doi":"https://doi.org/10.1109/icassp.2010.5495096","title":"A discriminative model for continuous speech recognition based on Weighted Finite State Transducers","display_name":"A discriminative model for continuous speech recognition based on Weighted Finite State Transducers","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W1984906370","doi":"https://doi.org/10.1109/icassp.2010.5495096","mag":"1984906370"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001291873"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":1.3572,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83705335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"4922","last_page":"4925"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9284372925758362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474413514137268},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6017932891845703},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5951610207557678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5818927884101868},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4856806993484497},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4739553928375244},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.42768359184265137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4134792387485504},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40031611919403076},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2682373821735382},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24956762790679932}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9284372925758362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474413514137268},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6017932891845703},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5951610207557678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5818927884101868},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4856806993484497},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4739553928375244},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.42768359184265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4134792387485504},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40031611919403076},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2682373821735382},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24956762790679932}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W191444391","https://openalex.org/W203133937","https://openalex.org/W2046932483","https://openalex.org/W2100474170","https://openalex.org/W2106404689","https://openalex.org/W2131964822","https://openalex.org/W2138889249","https://openalex.org/W2150907703","https://openalex.org/W2154075111","https://openalex.org/W2156615793","https://openalex.org/W2158148237","https://openalex.org/W2158808283","https://openalex.org/W2336725036","https://openalex.org/W6662227517","https://openalex.org/W6682398751"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W2167155152","https://openalex.org/W161037869","https://openalex.org/W2121652828","https://openalex.org/W2004453227","https://openalex.org/W3033124456"],"abstract_inverted_index":{"This":[0,91],"paper":[1,92],"proposes":[2],"a":[3,15,23,31,84,96,138,147],"discriminative":[4,109,193],"model":[5,17,98,119,169],"for":[6,39],"speech":[7,16,36,97],"recognition":[8,178],"that":[9],"directly":[10,103],"optimizes":[11],"the":[12,20,27,105,126,134,168,173,181],"parameters":[13,114,153],"of":[14,22,29,51,72,130,137],"represented":[18],"in":[19,100,104,115,133],"form":[21],"decoding":[24,135],"graph.":[25],"In":[26],"process":[28],"recognition,":[30],"decoder,":[32,85],"given":[33],"an":[34,40,65,77,157],"input":[35],"signal,":[37],"searches":[38],"appropriate":[41],"label":[42],"sequence":[43],"among":[44],"possible":[45],"combinations":[46],"from":[47],"separate":[48,89],"knowledge":[49,67],"sources":[50],"speech,":[52],"e.g.,":[53],"acoustic,":[54],"lexicon,":[55],"and":[56,75,185],"language":[57,118],"models.":[58],"It":[59],"is":[60,70,123,171],"more":[61],"reasonable":[62],"to":[63,80,87,94,144,187],"use":[64,88],"integrated":[66],"source,":[68],"which":[69,112],"composed":[71,99],"these":[73],"models":[74],"forms":[76],"overall":[78],"space":[79],"be":[81],"searched":[82],"by":[83,156],"than":[86,180,192],"ones.":[90],"aims":[93],"estimate":[95,113],"this":[101],"way":[102],"search":[106],"network,":[107],"unlike":[108],"training":[110,194],"approaches,":[111],"acoustic":[116],"or":[117,188],"layers.":[120],"Our":[121],"approach":[122,175],"formulated":[124],"as":[125],"weight":[127,152],"parameter":[128],"optimization":[129],"log-linear":[131],"distributions":[132],"arcs":[136],"Weighted":[139],"Finite":[140],"State":[141],"Transducer":[142],"(WFST)":[143],"efficiently":[145],"handle":[146],"large":[148],"network":[149],"statically.":[150],"The":[151,161],"are":[154],"estimated":[155],"averaged":[158],"perceptron":[159],"algorithm.":[160],"experimental":[162],"results":[163],"show":[164],"that,":[165],"especially":[166],"when":[167],"size":[170],"small,":[172],"proposed":[174],"provided":[176],"better":[177,190],"performance":[179,191],"conventional":[182],"maximum":[183],"likelihood":[184],"comparable":[186],"slightly":[189],"approaches.":[195]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}