{"id":"https://openalex.org/W2147243662","doi":"https://doi.org/10.1109/iscslp.2010.5684903","title":"Improving Mandarin Chinese STT system with Random Forests language models","display_name":"Improving Mandarin Chinese STT system with Random Forests language models","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2147243662","doi":"https://doi.org/10.1109/iscslp.2010.5684903","mag":"2147243662"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2010.5684903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language 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/A5035766151","display_name":"Ilya Oparin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ilya Oparin","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France","LIMSI CNRS, Spoken Language Processing Group, B.P. 133, 91403 Orsay, cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, B.P. 133, 91403 Orsay, cedex, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062446882","display_name":"Lori Lamel","orcid":"https://orcid.org/0000-0001-7443-9938"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lori Lamel","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France","LIMSI CNRS, Spoken Language Processing Group, B.P. 133, 91403 Orsay, cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, B.P. 133, 91403 Orsay, cedex, France","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109214406","display_name":"Jean\u2010Luc Gauvain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Gauvain","raw_affiliation_strings":["LIMSI-CNRS, Orsay, France","LIMSI CNRS, Spoken Language Processing Group, B.P. 133, 91403 Orsay, cedex, France"],"affiliations":[{"raw_affiliation_string":"LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIMSI CNRS, Spoken Language Processing Group, B.P. 133, 91403 Orsay, cedex, France","institution_ids":["https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035766151"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210115485"],"apc_list":null,"apc_paid":null,"fwci":0.9021,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81420596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8968279361724854},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.8624143600463867},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.8580381870269775},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.759162425994873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7569715976715088},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7192806005477905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5206508040428162},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44510456919670105},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.43346288800239563},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.414716899394989},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37423622608184814},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15101200342178345},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0790143609046936}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8968279361724854},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8624143600463867},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.8580381870269775},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.759162425994873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569715976715088},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7192806005477905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5206508040428162},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44510456919670105},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.43346288800239563},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.414716899394989},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37423622608184814},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15101200342178345},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0790143609046936},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2010.5684903","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2010.5684903","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 7th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W33139488","https://openalex.org/W109703299","https://openalex.org/W180516261","https://openalex.org/W180685247","https://openalex.org/W2016243284","https://openalex.org/W2026339097","https://openalex.org/W2071315630","https://openalex.org/W2097427897","https://openalex.org/W2099345940","https://openalex.org/W2106459246","https://openalex.org/W2261756304","https://openalex.org/W2437096199","https://openalex.org/W6601376335","https://openalex.org/W6607426480","https://openalex.org/W6657162565"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2084531783","https://openalex.org/W2020757772","https://openalex.org/W2902731467"],"abstract_inverted_index":{"The":[0],"goal":[1,118],"of":[2,10,26,51,135],"this":[3,46,103],"work":[4,47],"is":[5,70,105],"to":[6,22,65,115,123],"assess":[7],"the":[8,24,48,52,89,117,128,142],"capacity":[9],"random":[11,33,109,125],"forest":[12,110],"language":[13,74,111,138],"models":[14],"estimated":[15],"on":[16,77,127],"a":[17,62,73,78,108,133,150],"very":[18,79],"large":[19,80,147],"text":[20,81],"corpus":[21,82],"improve":[23,66],"performance":[25],"an":[27],"STT":[28,57],"system.":[29],"Previous":[30],"experiments":[31],"with":[32,38,107],"forests":[34,126],"were":[35],"mainly":[36],"concerned":[37],"small":[39],"or":[40],"medium":[41],"size":[42],"data":[43,130,148,163],"tasks.":[44,164],"In":[45,113],"development":[49],"version":[50],"2009":[53],"LIMSI":[54],"Mandarin":[55],"Chinese":[56],"system":[58,69],"was":[59],"chosen":[60],"as":[61],"challenging":[63],"baseline":[64,90,152],"upon.":[67],"This":[68],"characterized":[71],"by":[72],"model":[75,104,154],"trained":[76],"(over":[83],"3.2":[84],"billion":[85],"segmented":[86],"words)":[87],"making":[88],"4-gram":[91],"estimates":[92],"particularly":[93],"robust.":[94],"We":[95],"observed":[96],"moderate":[97],"perplexity":[98],"and":[99,131],"CER":[100],"improvements":[101,143],"when":[102],"interpolated":[106],"model.":[112],"order":[114],"attain":[116],"we":[119,144],"tried":[120],"different":[121],"strategies":[122],"build":[124],"available":[129],"introduced":[132],"Forest":[134],"Random":[136],"Forests":[137],"modeling":[139],"scheme.":[140],"However,":[141],"get":[145],"for":[146,161],"over":[149],"well-tuned":[151],"N-gram":[153],"are":[155],"less":[156],"impressive":[157],"than":[158],"those":[159],"reported":[160],"smaller":[162]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}