{"id":"https://openalex.org/W12168553","doi":"https://doi.org/10.21437/icslp.1998-649","title":"Source-extended language model for large vocabulary continuous speech recognition","display_name":"Source-extended language model for large vocabulary continuous speech recognition","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W12168553","doi":"https://doi.org/10.21437/icslp.1998-649","mag":"12168553"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-649","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","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/A5101188700","display_name":"Tetsunori Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tetsunori Kobayashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000195324","display_name":"Yosuke Wada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Wada","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103534950","display_name":"Norihiko Kobayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Norihiko Kobayashi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101188700"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00163294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0708","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.978600025177002,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9243999719619751,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/perplexity","display_name":"Perplexity","score":0.9760677814483643},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.8575409650802612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.828964352607727},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7547224164009094},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6711311340332031},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6640962362289429},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6114764213562012},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.594104528427124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5754174590110779},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.5242598056793213},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.5229492783546448},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.468166321516037},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4314330518245697},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4163699448108673},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28864312171936035},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.09875744581222534},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.09217968583106995},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08775901794433594},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07295119762420654}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9760677814483643},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.8575409650802612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828964352607727},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7547224164009094},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6711311340332031},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6640962362289429},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6114764213562012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.594104528427124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5754174590110779},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.5242598056793213},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.5229492783546448},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.468166321516037},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4314330518245697},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4163699448108673},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28864312171936035},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.09875744581222534},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.09217968583106995},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08775901794433594},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07295119762420654},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.1998-649","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1607753411","https://openalex.org/W1718044877","https://openalex.org/W2135854887","https://openalex.org/W2233241003"],"related_works":["https://openalex.org/W1903115690","https://openalex.org/W2397861987","https://openalex.org/W2041167939","https://openalex.org/W2223833155","https://openalex.org/W2940857995","https://openalex.org/W2020757772","https://openalex.org/W2250909759","https://openalex.org/W2056250865","https://openalex.org/W4327499987","https://openalex.org/W2105076537"],"abstract_inverted_index":{"Information":[0],"source":[1,19,29,41,68,76],"extension":[2,20,42,79],"is":[3,109,118,128],"utilized":[4],"to":[5,26,113,122,132],"improve":[6],"the":[7,22,27,33,51,55,63,85,104,106],"language":[8,35,56],"model":[9,23,36],"for":[10,54],"large":[11],"vocabulary":[12],"continuous":[13],"speech":[14,101],"recognition":[15,93,126],"(LVCSR).":[16],"McMillan's":[17],"theory,":[18],"make":[21],"entropy":[24],"close":[25],"real":[28],"entropy,":[30],"implies":[31],"that":[32],"better":[34],"can":[37],"be":[38],"obtained":[39],"by":[40],"(making":[43],"new":[44,52],"unit":[45,53],"through":[46],"word":[47],"concatenations":[48],"and":[49,80,92,99,115],"using":[50,95],"modeling).":[57],"In":[58],"this":[59,67],"paper,":[60],"we":[61,71],"examined":[62],"e":[64,86],"ectiveness":[65],"of":[66,75,90],"extension.":[69,82],"Here,":[70],"tested":[72,84],"two":[73],"methods":[74],"extension:":[77],"frequency-based":[78],"entropy-based":[81],"We":[83],"ect":[87],"in":[88],"terms":[89],"perplexity":[91,108,117],"accuracy":[94,127],"Mainichi":[96],"newspaper":[97],"articles":[98],"JNAS":[100],"corpus.":[102],"As":[103],"results,":[105],"bi-gram":[107],"improved":[110,119,129],"from":[111,120,130],"98.6":[112],"70.8":[114],"tri-gram":[116],"41.9":[121],"26.4.":[123],"The":[124],"bigram-based":[125],"79.8%":[131],"85.3%.":[133]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}