{"id":"https://openalex.org/W2082890803","doi":"https://doi.org/10.1109/tasl.2012.2199112","title":"Structural Classification Methods Based on Weighted Finite-State Transducers for Automatic Speech Recognition","display_name":"Structural Classification Methods Based on Weighted Finite-State Transducers for Automatic Speech Recognition","publication_year":2012,"publication_date":"2012-08-08","ids":{"openalex":"https://openalex.org/W2082890803","doi":"https://doi.org/10.1109/tasl.2012.2199112","mag":"2082890803"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2012.2199112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2199112","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/A5102252420","display_name":"Yotaro Kubo","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":true,"raw_author_name":"Yotaro Kubo","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA","NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, 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, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, 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, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102252420"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.5688,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90339724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"20","issue":"8","first_page":"2240","last_page":"2251"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9976000189781189,"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":0.8115084171295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7937741279602051},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7210472226142883},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6841564178466797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6338782906532288},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.6291015148162842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543173015117645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4249327778816223},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4023733139038086},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2162705361843109}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8115084171295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7937741279602051},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7210472226142883},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6841564178466797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6338782906532288},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.6291015148162842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543173015117645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4249327778816223},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4023733139038086},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2162705361843109}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2012.2199112","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2012.2199112","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"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":57,"referenced_works":["https://openalex.org/W34922426","https://openalex.org/W81231479","https://openalex.org/W91928571","https://openalex.org/W98722733","https://openalex.org/W191444391","https://openalex.org/W203133937","https://openalex.org/W853436745","https://openalex.org/W1499021337","https://openalex.org/W1534536260","https://openalex.org/W1978381081","https://openalex.org/W1979711143","https://openalex.org/W1984196678","https://openalex.org/W2005076803","https://openalex.org/W2005733316","https://openalex.org/W2008652694","https://openalex.org/W2036912417","https://openalex.org/W2046932483","https://openalex.org/W2053567709","https://openalex.org/W2103359087","https://openalex.org/W2105842272","https://openalex.org/W2117027359","https://openalex.org/W2125234026","https://openalex.org/W2131033001","https://openalex.org/W2131702393","https://openalex.org/W2134861448","https://openalex.org/W2137880010","https://openalex.org/W2138302120","https://openalex.org/W2138889249","https://openalex.org/W2141540671","https://openalex.org/W2143908786","https://openalex.org/W2147880316","https://openalex.org/W2150907703","https://openalex.org/W2153773386","https://openalex.org/W2154075111","https://openalex.org/W2154198224","https://openalex.org/W2156515921","https://openalex.org/W2156615793","https://openalex.org/W2156621455","https://openalex.org/W2158148237","https://openalex.org/W2165485601","https://openalex.org/W2167270514","https://openalex.org/W2168199160","https://openalex.org/W2169384404","https://openalex.org/W2295757520","https://openalex.org/W3141933106","https://openalex.org/W4230318854","https://openalex.org/W4249572517","https://openalex.org/W4285719527","https://openalex.org/W6603713578","https://openalex.org/W6604053746","https://openalex.org/W6651845459","https://openalex.org/W6675321185","https://openalex.org/W6675783020","https://openalex.org/W6680748266","https://openalex.org/W6682082992","https://openalex.org/W6682398751","https://openalex.org/W6684930139"],"related_works":["https://openalex.org/W2163278254","https://openalex.org/W155708904","https://openalex.org/W1574213390","https://openalex.org/W2167155152","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070"],"abstract_inverted_index":{"The":[0],"potential":[1],"of":[2,24,29,42,48,68,95,168,208],"structural":[3,33,149],"classification":[4,34,150],"methods":[5,147],"for":[6,55,102,134,148,176],"automatic":[7],"speech":[8,15],"recognition":[9,181],"(ASR)":[10],"has":[11],"been":[12],"attracting":[13],"the":[14,21,32,40,45,66,75,79,93,96,152,155,166,177,183,188,196,200,205,209,213],"community":[16],"since":[17,122],"they":[18],"can":[19],"realize":[20],"unified":[22],"modeling":[23],"acoustic":[25,81],"and":[26,44,82,138,158,187],"linguistic":[27],"aspects":[28],"recognizers.":[30],"However,":[31],"approaches":[35],"involve":[36],"well-known":[37],"tradeoffs":[38],"between":[39],"richness":[41],"features":[43,62],"computational":[46,206],"efficiency":[47,207],"decoders.":[49],"If":[50],"we":[51,144,172],"are":[52,132,216],"to":[53,64,74],"employ,":[54],"example,":[56],"a":[57,114],"frame-synchronous":[58],"one-pass":[59],"decoding":[60,117,124],"technique,":[61],"considered":[63],"calculate":[65],"likelihood":[67,130],"each":[69,135],"hypothesis":[70],"must":[71],"be":[72],"restricted":[73],"same":[76],"form":[77],"as":[78],"conventional":[80],"language":[83],"models.":[84],"This":[85],"paper":[86],"tackles":[87],"this":[88,142],"limitation":[89],"directly":[90],"by":[91],"exploiting":[92],"structure":[94],"weighted":[97],"finite-state":[98],"transducers":[99],"(WFSTs)":[100],"used":[101],"decoding.":[103],"Although":[104],"WFST":[105],"arcs":[106],"provide":[107],"rich":[108],"contextual":[109],"information,":[110],"close":[111],"integration":[112],"with":[113,151,219],"computationally":[115],"efficient":[116],"technique":[118],"is":[119],"still":[120],"possible":[121],"most":[123],"techniques":[125,222],"only":[126],"require":[127],"that":[128,195],"their":[129],"functions":[131],"factorizable":[133],"decoder":[136],"arc":[137],"time":[139],"frame.":[140],"In":[141],"paper,":[143],"compare":[145],"two":[146,170],"WFST-based":[153],"features;":[154],"structured":[156],"perceptron":[157],"conditional":[159],"random":[160],"field":[161],"(CRF)":[162],"techniques.":[163],"To":[164],"analyze":[165],"advantages":[167],"these":[169],"classifiers,":[171],"present":[173],"experimental":[174],"results":[175],"TIMIT":[178],"continuous":[179],"phoneme":[180],"task,":[182,186],"WSJ":[184],"transcription":[185,191],"MIT":[189],"lecture":[190],"task.":[192],"We":[193],"confirmed":[194],"proposed":[197],"approach":[198],"improved":[199],"ASR":[201],"performance":[202],"without":[203],"sacrificing":[204],"decoders,":[210],"even":[211],"though":[212],"baseline":[214],"systems":[215],"already":[217],"trained":[218],"discriminative":[220],"training":[221],"(e.g.,":[223],"MPE).":[224]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}