{"id":"https://openalex.org/W1987408080","doi":"https://doi.org/10.1109/asru.2013.6707697","title":"Learning a subword vocabulary based on unigram likelihood","display_name":"Learning a subword vocabulary based on unigram likelihood","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1987408080","doi":"https://doi.org/10.1109/asru.2013.6707697","mag":"1987408080"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5030484123","display_name":"Matti Varjokallio","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Matti Varjokallio","raw_affiliation_strings":["Dept. of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Dept. of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Dept. of Signal Processing and Acoustics, Aalto University, Espoo, Finland","Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Dept. of Signal Processing and Acoustics, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Dept. of Signal Process. & Acoust., Aalto Univ., Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003986900","display_name":"S\u00e1mi Virpioja","orcid":"https://orcid.org/0000-0002-3568-150X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Sami Virpioja","raw_affiliation_strings":["Dept. of Information and Computer Science, Aalto University, Espoo, Finland","Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Dept. of Information and Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030484123"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":2.4908,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90034487,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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":0.9934999942779541,"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":0.8377484083175659},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7956832051277161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7064287662506104},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6747239828109741},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6444451808929443},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5373448729515076},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5319395661354065},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.49431896209716797},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4704037308692932},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09879428148269653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8377484083175659},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7956832051277161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7064287662506104},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6747239828109741},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6444451808929443},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5373448729515076},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5319395661354065},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.49431896209716797},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4704037308692932},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09879428148269653},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W10704533","https://openalex.org/W23024349","https://openalex.org/W126222424","https://openalex.org/W1952669422","https://openalex.org/W2026689784","https://openalex.org/W2032942114","https://openalex.org/W2069712814","https://openalex.org/W2088857750","https://openalex.org/W2097978681","https://openalex.org/W2111305191","https://openalex.org/W2117621558","https://openalex.org/W2121299803","https://openalex.org/W2122228338","https://openalex.org/W2125838338","https://openalex.org/W2131111393","https://openalex.org/W2142937603","https://openalex.org/W2156700117","https://openalex.org/W2157301369","https://openalex.org/W2251667755","https://openalex.org/W2295551984","https://openalex.org/W3183153947","https://openalex.org/W6605210145","https://openalex.org/W6640984349","https://openalex.org/W6674334065","https://openalex.org/W6678164431","https://openalex.org/W6691359957","https://openalex.org/W6697190839","https://openalex.org/W6798472456"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W2047632477","https://openalex.org/W3041490575","https://openalex.org/W1992088235","https://openalex.org/W2970690932"],"abstract_inverted_index":{"Using":[0],"words":[1],"as":[2],"vocabulary":[3],"units":[4,21],"for":[5,12,25,34,73],"tasks":[6],"like":[7],"speech":[8,85],"recognition":[9,86],"is":[10,50,66],"infeasible":[11],"many":[13],"morphologically":[14],"rich":[15],"languages,":[16],"including":[17],"Finnish.":[18],"Thus,":[19],"subword":[20,37],"are":[22],"commonly":[23],"used":[24],"language":[26],"modeling.":[27],"This":[28],"work":[29],"presents":[30],"a":[31,36,45,56,70],"novel":[32],"algorithm":[33],"creating":[35],"vocabulary,":[38],"based":[39],"on":[40],"the":[41,63,74],"unigram":[42],"likelihood":[43],"of":[44,62,76],"text":[46,64],"corpus.":[47],"The":[48],"method":[49],"evaluated":[51],"with":[52],"entropy":[53,61],"measure":[54],"and":[55],"Finnish":[57],"LVCSR":[58],"task.":[59],"Unigram":[60],"corpus":[65],"shown":[67],"to":[68],"be":[69],"good":[71],"indicator":[72],"quality":[75],"higher":[77],"order":[78],"n-gram":[79],"models,":[80],"also":[81],"resulting":[82],"in":[83],"high":[84],"accuracy.":[87]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}