{"id":"https://openalex.org/W2126077750","doi":"https://doi.org/10.1109/icassp.2008.4518590","title":"Improved phonotactic language identification using random forest language models","display_name":"Improved phonotactic language identification using random forest language models","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2126077750","doi":"https://doi.org/10.1109/icassp.2008.4518590","mag":"2126077750"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518590","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 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/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XiaoRui Wang","raw_affiliation_strings":["Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103143080","display_name":"Shijin Wang","orcid":"https://orcid.org/0000-0002-4340-7420"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ShiJin Wang","raw_affiliation_strings":["Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110832899","display_name":"Jiaen Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JiaEn Liang","raw_affiliation_strings":["Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Media Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Digital Media Content Technology Research Center, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Media Content Technology Research Center, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Digital Media Content Technol. Res. Center, Chinese Acad. of Sci., Beijing","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.23290693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4237","last_page":"4240"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996399998664856,"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/phonotactics","display_name":"Phonotactics","score":0.8633031845092773},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.8189384937286377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8058138489723206},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6763427257537842},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6255942583084106},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5700690746307373},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5680955052375793},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.5573682188987732},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5376876592636108},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5025906562805176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.501629114151001},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.49463340640068054},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4555169641971588},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4426654577255249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32422390580177307},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.2279077172279358},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17825615406036377},{"id":"https://openalex.org/keywords/phonology","display_name":"Phonology","score":0.11173191666603088},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0783517062664032}],"concepts":[{"id":"https://openalex.org/C4768521","wikidata":"https://www.wikidata.org/wiki/Q512366","display_name":"Phonotactics","level":3,"score":0.8633031845092773},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.8189384937286377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058138489723206},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6763427257537842},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6255942583084106},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5700690746307373},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5680955052375793},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.5573682188987732},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5376876592636108},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5025906562805176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501629114151001},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.49463340640068054},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4555169641971588},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4426654577255249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32422390580177307},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2279077172279358},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17825615406036377},{"id":"https://openalex.org/C148934300","wikidata":"https://www.wikidata.org/wiki/Q40998","display_name":"Phonology","level":2,"score":0.11173191666603088},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0783517062664032},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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.2008.4518590","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518590","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.699999988079071,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W141449985","https://openalex.org/W151003953","https://openalex.org/W156922528","https://openalex.org/W180516261","https://openalex.org/W180685247","https://openalex.org/W2071315630","https://openalex.org/W2113832997","https://openalex.org/W2172287020","https://openalex.org/W2398046886","https://openalex.org/W4239209816","https://openalex.org/W6606123296"],"related_works":["https://openalex.org/W2105076537","https://openalex.org/W2020757772","https://openalex.org/W2072223048","https://openalex.org/W2041167939","https://openalex.org/W2950575438","https://openalex.org/W2002221802","https://openalex.org/W2250909759","https://openalex.org/W1975573722","https://openalex.org/W1620568205","https://openalex.org/W1823613926"],"abstract_inverted_index":{"Recently":[0],"a":[1,35,49,78,102],"new":[2],"language":[3,8,30,54],"model,":[4],"the":[5,27,68,92,98],"random":[6],"forest":[7],"model":[9],"(RFLM),":[10],"has":[11],"been":[12],"proposed":[13,34],"and":[14,83,97],"shown":[15],"encouraging":[16],"results":[17],"in":[18,101],"speech":[19],"recognition":[20,55],"tasks.":[21,32],"In":[22],"this":[23],"paper":[24],"we":[25],"applied":[26],"RFLM":[28,59,73],"to":[29,39,80],"identification":[31],"We":[33,88],"shared":[36],"backoff":[37],"smoothing":[38],"deal":[40],"with":[41,67],"data":[42],"sparseness":[43],"problem.":[44],"Experiments":[45],"were":[46],"conducted":[47],"on":[48],"subset":[50],"of":[51],"NIST":[52],"2003":[53],"evaluation":[56],"data.":[57],"The":[58,72],"obtained":[60],"15.7%":[61],"relative":[62],"error":[63],"rate":[64],"reduction":[65],"comparing":[66],"standard":[69],"trigram":[70],"LM.":[71],"can":[74],"be":[75],"used":[76],"as":[77],"counterpart":[79],"n-gram":[81],"LM":[82],"BTLM":[84],"for":[85],"system":[86,95],"fusion.":[87],"also":[89],"empirically":[90],"studied":[91],"relation":[93],"between":[94],"performance":[96],"tree":[99],"numbers":[100],"RFLM.":[103]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}