{"id":"https://openalex.org/W2171523149","doi":"https://doi.org/10.1109/icassp.2005.1415085","title":"Efficient Generation of high-order context-dependent Weighted Finite State Transducers for Speech Recognition","display_name":"Efficient Generation of high-order context-dependent Weighted Finite State Transducers for Speech Recognition","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2171523149","doi":"https://doi.org/10.1109/icassp.2005.1415085","mag":"2171523149"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5061935473","display_name":"Maria Schuster","orcid":"https://orcid.org/0000-0001-9122-7478"},"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":"M. Schuster","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/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":"T. 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061935473"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.2591,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89648146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"201","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9961000084877014,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.8045265674591064},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6451472043991089},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6113088130950928},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5511342287063599},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5407950282096863},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5134842991828918},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5007033348083496},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.48573046922683716},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.475582480430603},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.46985092759132385},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.4328348636627197},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42930367588996887},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42727115750312805},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3441861867904663},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30454641580581665},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.29926198720932007},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09621787071228027},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08958104252815247},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08527159690856934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045265674591064},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6451472043991089},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6113088130950928},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5511342287063599},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5407950282096863},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5134842991828918},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5007033348083496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.48573046922683716},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.475582480430603},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.46985092759132385},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.4328348636627197},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42930367588996887},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42727115750312805},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3441861867904663},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30454641580581665},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29926198720932007},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09621787071228027},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08958104252815247},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08527159690856934},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W12115718","https://openalex.org/W87954838","https://openalex.org/W175231330","https://openalex.org/W1508752711","https://openalex.org/W2046932483","https://openalex.org/W2144462324","https://openalex.org/W2168941687","https://openalex.org/W2336725036","https://openalex.org/W6600511685","https://openalex.org/W6603550504","https://openalex.org/W6607077592","https://openalex.org/W6630493794","https://openalex.org/W6662227517"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W1591475660","https://openalex.org/W2012283803","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W4232940367"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3,32,51],"algorithm":[4,33],"for":[5,13],"efficient":[6],"building":[7],"of":[8,20,38,141],"weighted":[9],"finite":[10],"state":[11],"transducers":[12,42],"speech":[14,115],"recognition":[15,106,127],"when":[16],"high-order":[17,85],"context-dependent":[18],"models":[19,88],"order":[21],"K>3":[22],"(triphones)":[23],"with":[24,50,89,132],"tied":[25],"states":[26],"are":[27],"used.":[28],"We":[29],"show":[30],"how":[31],"to":[34,57,83,124],"build":[35],"a":[36,94,111,133],"part":[37],"the":[39,45,77,118],"needed":[40],"composed":[41],"directly":[43,92],"from":[44],"decision":[46],"trees":[47],"in":[48,71,137],"combination":[49],"improved":[52],"compilation":[53],"process":[54],"can":[55],"lead":[56],"much":[58],"faster,":[59],"simpler":[60],"and":[61,108],"more":[62],"memory-efficient":[63],"compilation.":[64],"In":[65],"our":[66],"case,":[67],"it":[68,80,121],"also":[69],"resulted":[70],"substantially":[72],"smaller":[73],"final":[74,103],"networks.":[75],"With":[76],"described":[78],"algorithm,":[79,120],"is":[81,122],"simple":[82],"use":[84],"full":[86,129],"cross-word":[87],"little":[90],"overhead":[91],"within":[93],"one-pass":[95],"time-synchronous":[96],"search,":[97],"which":[98],"we":[99],"test":[100],"comparing":[101],"resulting":[102],"network":[104],"sizes,":[105],"rates":[107],"speed":[109],"on":[110],"large,":[112],"spontaneous":[113],"Japanese":[114],"database.":[116],"Using":[117],"proposed":[119],"possible":[123],"do":[125],"real-time":[126],"using":[128],"crossword":[130],"quinphones":[131],"large":[134],"acoustic":[135],"model":[136],"about":[138,144],"125":[139],"MB":[140],"memory":[142],"at":[143],"9%":[145],"search":[146],"error.":[147]},"counts_by_year":[{"year":2014,"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"}