{"id":"https://openalex.org/W2142937603","doi":"https://doi.org/10.1109/tasl.2008.2012323","title":"Importance of High-Order N-Gram Models in Morph-Based Speech Recognition","display_name":"Importance of High-Order N-Gram Models in Morph-Based Speech Recognition","publication_year":2009,"publication_date":"2009-03-30","ids":{"openalex":"https://openalex.org/W2142937603","doi":"https://doi.org/10.1109/tasl.2008.2012323","mag":"2142937603"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2008.2012323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2012323","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5085765257","display_name":"Teemu Hirsim\u00e4ki","orcid":null},"institutions":[{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Teemu Hirsimaki","raw_affiliation_strings":["Adaptive Informatics Research Center, Helsinki University of Technology, Espoo, Finland","Adaptive Inf. Res. Center, Helsinki Univ. of Technol., Espoo"],"affiliations":[{"raw_affiliation_string":"Adaptive Informatics Research Center, Helsinki University of Technology, Espoo, Finland","institution_ids":["https://openalex.org/I32943570"]},{"raw_affiliation_string":"Adaptive Inf. Res. Center, Helsinki Univ. of Technol., Espoo","institution_ids":["https://openalex.org/I32943570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046171140","display_name":"Janne Pylkk\u00f6nen","orcid":null},"institutions":[{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Janne Pylkkonen","raw_affiliation_strings":["Adaptive Informatics Research Center, Helsinki University of Technology, Espoo, Finland","Adaptive Inf. Res. Center, Helsinki Univ. of Technol., Espoo"],"affiliations":[{"raw_affiliation_string":"Adaptive Informatics Research Center, Helsinki University of Technology, Espoo, Finland","institution_ids":["https://openalex.org/I32943570"]},{"raw_affiliation_string":"Adaptive Inf. Res. Center, Helsinki Univ. of Technol., Espoo","institution_ids":["https://openalex.org/I32943570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I32943570","display_name":"Helsinki Institute for Information Technology","ror":"https://ror.org/05kph4940","country_code":"FI","type":"facility","lineage":["https://openalex.org/I133731052","https://openalex.org/I32943570","https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Adaptive Informatics Research Center, Helsinki University of Technology, Espoo, Finland","Adaptive Inf. Res. Center, Helsinki Univ. of Technol., Espoo"],"affiliations":[{"raw_affiliation_string":"Adaptive Informatics Research Center, Helsinki University of Technology, Espoo, Finland","institution_ids":["https://openalex.org/I32943570"]},{"raw_affiliation_string":"Adaptive Inf. Res. Center, Helsinki Univ. of Technol., Espoo","institution_ids":["https://openalex.org/I32943570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085765257"],"corresponding_institution_ids":["https://openalex.org/I32943570"],"apc_list":null,"apc_paid":null,"fwci":13.0855,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.9886574,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"4","first_page":"724","last_page":"732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/agglutinative-language","display_name":"Agglutinative language","score":0.9254155158996582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486605644226074},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6455169320106506},{"id":"https://openalex.org/keywords/estonian","display_name":"Estonian","score":0.5929890871047974},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.577441394329071},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5432752966880798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5299777984619141},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5199974179267883},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.44740039110183716},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.4469642639160156},{"id":"https://openalex.org/keywords/word-order","display_name":"Word order","score":0.4296553432941437},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4138449430465698},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2671874165534973},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.20126914978027344}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.9254155158996582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486605644226074},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6455169320106506},{"id":"https://openalex.org/C2776092919","wikidata":"https://www.wikidata.org/wiki/Q9072","display_name":"Estonian","level":2,"score":0.5929890871047974},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.577441394329071},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5432752966880798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5299777984619141},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5199974179267883},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.44740039110183716},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.4469642639160156},{"id":"https://openalex.org/C70777604","wikidata":"https://www.wikidata.org/wiki/Q257885","display_name":"Word order","level":2,"score":0.4296553432941437},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4138449430465698},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2671874165534973},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.20126914978027344},{"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/tasl.2008.2012323","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2008.2012323","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W813000","https://openalex.org/W15942306","https://openalex.org/W23024349","https://openalex.org/W27187656","https://openalex.org/W49695535","https://openalex.org/W76921649","https://openalex.org/W112233275","https://openalex.org/W139293362","https://openalex.org/W153320552","https://openalex.org/W262058279","https://openalex.org/W1494693235","https://openalex.org/W1501633760","https://openalex.org/W1585240873","https://openalex.org/W1600529453","https://openalex.org/W1719940802","https://openalex.org/W1797288984","https://openalex.org/W1884028435","https://openalex.org/W2032942114","https://openalex.org/W2042783153","https://openalex.org/W2046932483","https://openalex.org/W2050938027","https://openalex.org/W2069712814","https://openalex.org/W2077444666","https://openalex.org/W2090750282","https://openalex.org/W2103589071","https://openalex.org/W2115084322","https://openalex.org/W2128014038","https://openalex.org/W2129812225","https://openalex.org/W2133692508","https://openalex.org/W2134501463","https://openalex.org/W2156700117","https://openalex.org/W2158195707","https://openalex.org/W2190094906","https://openalex.org/W2902905787","https://openalex.org/W3183153947","https://openalex.org/W6600665201","https://openalex.org/W6600942878","https://openalex.org/W6603071697","https://openalex.org/W6629517120","https://openalex.org/W6638218882","https://openalex.org/W6679867915"],"related_works":["https://openalex.org/W2292235321","https://openalex.org/W2220770597","https://openalex.org/W2285522033","https://openalex.org/W4327524755","https://openalex.org/W2295293153","https://openalex.org/W2170242713","https://openalex.org/W2125852914","https://openalex.org/W4255406899","https://openalex.org/W4229450305","https://openalex.org/W1965272602"],"abstract_inverted_index":{"Speech":[0,107],"recognition":[1,108,147,159],"systems":[2],"trained":[3,83,92],"for":[4,141],"morphologically":[5],"rich":[6],"languages":[7],"face":[8],"the":[9,25,29,32,43,70,79,151,158],"problem":[10],"of":[11,31,72,87,146,160],"vocabulary":[12,33,97],"growth":[13],"caused":[14],"by":[15],"prefixes,":[16],"suffixes,":[17],"inflections,":[18],"and":[19,34,117,121],"compound":[20],"words.":[21,89,163],"Solutions":[22],"proposed":[23],"in":[24,40,132],"literature":[26],"include":[27],"increasing":[28],"size":[30],"segmenting":[35],"words":[36],"into":[37],"morphs.":[38],"However,":[39],"many":[41],"cases,":[42],"methods":[44],"have":[45,61],"only":[46],"been":[47],"experimented":[48],"with":[49,100],"low-order":[50],"n-gram":[51,76],"models":[52,57,77,81,91,101,128,155],"or":[53],"compared":[54,99],"to":[55],"word-based":[56],"that":[58,126,150],"do":[59],"not":[60],"very":[62,95],"large":[63,96],"vocabularies.":[64],"In":[65],"this":[66],"paper,":[67],"we":[68],"study":[69],"importance":[71],"using":[73],"high-order":[74,127,152],"variable-length":[75],"when":[78,137],"language":[80,154],"are":[82,98,110,139],"over":[84],"morphs":[85],"instead":[86],"whole":[88],"Language":[90],"on":[93,103,113],"a":[94],"based":[102],"different":[104],"morph":[105,153],"segmentations.":[106],"experiments":[109],"carried":[111],"out":[112],"two":[114],"highly":[115],"inflecting":[116],"agglutinative":[118],"languages,":[119],"Finnish":[120],"Estonian.":[122],"The":[123,144],"results":[124],"suggest":[125],"can":[129],"be":[130],"essential":[131],"morph-based":[133],"speech":[134],"recognition,":[135],"even":[136],"lattices":[138],"generated":[140],"two-pass":[142],"recognition.":[143],"analysis":[145],"errors":[148],"reveal":[149],"improve":[156],"especially":[157],"previously":[161],"unseen":[162]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}