{"id":"https://openalex.org/W1978434663","doi":"https://doi.org/10.1109/icassp.2002.5743817","title":"Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation","display_name":"Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1978434663","doi":"https://doi.org/10.1109/icassp.2002.5743817","mag":"1978434663"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743817","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5017400582","display_name":"Daniel Willett","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":"Daniel Willett","raw_affiliation_strings":["Speech Open Lab, NTT Corporation, Soraku-gun, Kyoto, Japan","Speech Open Lab, NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Speech Open Lab, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"Speech Open Lab, NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"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":"Shigeru Katagiri","raw_affiliation_strings":["Speech Open Lab, NTT Corporation, Soraku-gun, Kyoto, Japan","Speech Open Lab, NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Speech Open Lab, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"Speech Open Lab, NTT Communication Science Laboratories, NTT Corporation, 2-4, Hikaridai, Seika-cho, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017400582"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.1305,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88431877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"713"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9990000128746033,"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":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8057949542999268},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6847245693206787},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6172839403152466},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5993332862854004},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5745835900306702},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5013120174407959},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.4662206470966339},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.461703360080719},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45772725343704224},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.44453299045562744},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4412137567996979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3509330153465271},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29147398471832275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057949542999268},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6847245693206787},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6172839403152466},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5993332862854004},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5745835900306702},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5013120174407959},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.4662206470966339},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.461703360080719},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45772725343704224},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.44453299045562744},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4412137567996979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3509330153465271},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29147398471832275},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743817","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743817","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W10656737","https://openalex.org/W27187656","https://openalex.org/W131831529","https://openalex.org/W1503102241","https://openalex.org/W1625762979","https://openalex.org/W1967325250","https://openalex.org/W2043547528","https://openalex.org/W2064283427","https://openalex.org/W2114916462","https://openalex.org/W2137446469","https://openalex.org/W2149298150","https://openalex.org/W6600442302","https://openalex.org/W6601066586","https://openalex.org/W6605302315","https://openalex.org/W6630279880"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2386035178"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"and":[3,94],"evaluates":[4],"our":[5],"recent":[6],"efforts":[7],"on":[8,67,82],"efficient":[9],"decoding":[10],"for":[11,30,38],"Large":[12],"Vocabulary":[13],"Continuous":[14],"Speech":[15],"Recognition":[16],"in":[17,49,73,108],"the":[18,50,57,61,74,101,121,125,131],"framework":[19],"of":[20,60,87,115,124],"Weighted":[21],"Finite":[22],"State":[23],"Transducers.":[24],"We":[25],"evaluate":[26],"on-the-fly":[27,116],"transducer":[28],"composition":[29,52,118],"reduced":[31],"memory":[32,144],"consumption":[33],"combined":[34],"with":[35,119,141],"weight":[36,54],"smearing":[37],"a":[39,83,110,134],"more":[40,65],"time-synchronous":[41],"language":[42,96,126],"model":[43,127],"incorporation.":[44],"It":[45],"turns":[46],"out":[47,81,105],"that":[48],"on-line":[51],"mode":[53],"smoothing":[55],"within":[56],"static":[58],"part":[59,123],"network":[62,117,132],"is":[63,103],"even":[64],"beneficial":[66],"run-time":[68,137],"to":[69,138],"accuracy":[70,139],"ratio":[71,140],"than":[72],"fully":[75,106],"precompiled":[76],"case.":[77],"Evaluations":[78],"are":[79],"carried":[80,104],"state-of-the-art":[84],"recognition":[85],"system":[86],"10k":[88],"words,":[89],"cross-word":[90],"triphone":[91],"acoustic":[92],"models":[93],"trigram":[95],"model.":[97],"In":[98],"this":[99],"scenario,":[100],"Viterbi-search":[102],"time-synchronously":[107],"only":[109,120,142],"single":[111],"pass.":[112],"The":[113],"combination":[114],"unigram":[122],"smoothly":[128],"compiled":[129],"into":[130],"achieves":[133],"remarkably":[135],"good":[136],"moderate":[143],"requirements.":[145]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}