{"id":"https://openalex.org/W23024349","doi":"https://doi.org/10.21437/interspeech.2006-330","title":"Unsupervised segmentation of words into morphemes - morpho challenge 2005 application to automatic speech recognition","display_name":"Unsupervised segmentation of words into morphemes - morpho challenge 2005 application to automatic speech recognition","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W23024349","doi":"https://doi.org/10.21437/interspeech.2006-330","mag":"23024349"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-330","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061159001","display_name":"Mathias Creutz","orcid":"https://orcid.org/0000-0003-1862-4172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathias Creutz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030484123","display_name":"Matti Varjokallio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matti Varjokallio","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097697762","display_name":"Ebru Arsoy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ebru Arsoy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055086464","display_name":"Murat Sara\u00e7lar","orcid":"https://orcid.org/0000-0002-7435-8510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murat Saraclar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043424064"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.3737,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97295361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"paper 1512","last_page":"Tue2A2O.1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":0.9955000281333923,"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":0.8837074637413025},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8359087705612183},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.7953291535377502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6818937063217163},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6733225584030151},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5603064298629761},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5467756986618042},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5003716945648193},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4649359881877899},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.44167137145996094},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4362497925758362},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18759238719940186}],"concepts":[{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.8837074637413025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359087705612183},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.7953291535377502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6818937063217163},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6733225584030151},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5603064298629761},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5467756986618042},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5003716945648193},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4649359881877899},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.44167137145996094},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4362497925758362},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18759238719940186},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2006-330","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.79.2460","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.2460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cis.hut.fi/mikkok/is06_mchall.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"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/W147140176","https://openalex.org/W148400104","https://openalex.org/W201532657","https://openalex.org/W605575788","https://openalex.org/W1719940802","https://openalex.org/W1904457459","https://openalex.org/W1970887833","https://openalex.org/W2042783153","https://openalex.org/W2069712814","https://openalex.org/W2117621558","https://openalex.org/W2725592455"],"related_works":["https://openalex.org/W2501899044","https://openalex.org/W2485012912","https://openalex.org/W2013556410","https://openalex.org/W1875057406","https://openalex.org/W2250538341","https://openalex.org/W2806955548","https://openalex.org/W2086703572","https://openalex.org/W2403232536","https://openalex.org/W4385342823","https://openalex.org/W2810296466"],"abstract_inverted_index":{"Within":[0],"the":[1,22,58,74,92,121,124],"EU":[2],"Network":[3],"of":[4,26,76,97,123],"Excellence":[5],"PASCAL,":[6],"a":[7,13],"challenge":[8,59],"was":[9],"organized":[10],"to":[11,80,119],"design":[12],"statistical":[14,50,86],"machine":[15,45],"learning":[16],"algorithm":[17],"that":[18],"segments":[19,95],"words":[20],"into":[21],"smallest":[23],"meaning-bearing":[24],"units":[25,34],"language,":[27],"morphemes.":[28],"Ideally,":[29],"these":[30,77],"are":[31],"basic":[32],"vocabulary":[33,82],"suitable":[35],"for":[36,103],"different":[37],"tasks,":[38],"such":[39],"as":[40],"speech":[41,83,128],"and":[42,49,60,106,111],"text":[43],"understanding,":[44],"translation,":[46],"information":[47],"retrieval,":[48],"language":[51,88,130],"modeling.":[52],"Twelve":[53],"research":[54],"groups":[55],"participated":[56],"in":[57],"had":[61],"submitted":[62],"segmentation":[63,78],"results":[64],"obtained":[65],"by":[66],"their":[67],"algorithms.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"evaluate":[73],"application":[75],"algorithms":[79],"large":[81],"recognition":[84],"using":[85],"n-gram":[87],"models":[89],"based":[90],"on":[91],"proposed":[93],"word":[94],"instead":[96],"entire":[98],"words.":[99],"Experiments":[100],"were":[101],"done":[102],"two":[104],"agglutinative":[105],"morphologically":[107],"rich":[108],"languages:":[109],"Finnish":[110],"Turkish.":[112],"We":[113],"also":[114],"investigate":[115],"combining":[116],"various":[117],"segmentations":[118],"improve":[120],"performance":[122],"recognizer.":[125],"Index":[126],"Terms:":[127],"recognition,":[129],"modelling,":[131],"morphemes,":[132],"unsupervised":[133],"learning.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}