{"id":"https://openalex.org/W2134501463","doi":"https://doi.org/10.21437/eurospeech.2003-640","title":"Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner","display_name":"Unlimited vocabulary speech recognition based on morphs discovered in an unsupervised manner","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W2134501463","doi":"https://doi.org/10.21437/eurospeech.2003-640","mag":"2134501463"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-640","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5040694307","display_name":"Vesa Siivola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vesa Siivola","raw_affiliation_strings":["Helsinki University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085765257","display_name":"Teemu Hirsim\u00e4ki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teemu Hirsimaki","raw_affiliation_strings":["Helsinki University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helsinki University of Technology","institution_ids":[]}]},{"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":["Department of Modern Languages 2010-2017"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Modern Languages 2010-2017","institution_ids":[]}]},{"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/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":["Aalto University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalto University","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2293","last_page":"2296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"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":0.996999979019165,"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":0.9941999912261963,"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":0.9894999861717224,"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/perplexity","display_name":"Perplexity","score":0.9395323991775513},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.9150650501251221},{"id":"https://openalex.org/keywords/agglutinative-language","display_name":"Agglutinative language","score":0.8426383137702942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8237550258636475},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7371011972427368},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7253166437149048},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.725022554397583},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7097182869911194},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6627389192581177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.612056314945221},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5516749024391174},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5498103499412537},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10391297936439514},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.06756243109703064}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9395323991775513},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.9150650501251221},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.8426383137702942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237550258636475},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7371011972427368},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7253166437149048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.725022554397583},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7097182869911194},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6627389192581177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612056314945221},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5516749024391174},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5498103499412537},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10391297936439514},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.06756243109703064},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/eurospeech.2003-640","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-640","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.1757","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.1757","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://lib.tkk.fi/diss/2006/isbn9512282119/article6.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.110.9735","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.110.9735","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/vsiivola/papers/es03_morph.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.57.7928","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.57.7928","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/es03_morph.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.99.7894","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.7894","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/mcreutz/papers/Siivola03.es_morph.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W139293362","https://openalex.org/W154368987","https://openalex.org/W1533169541","https://openalex.org/W1549285799","https://openalex.org/W1967325250","https://openalex.org/W2073076143","https://openalex.org/W2111305191","https://openalex.org/W2117621558"],"related_works":["https://openalex.org/W2053242504","https://openalex.org/W1903115690","https://openalex.org/W2397861987","https://openalex.org/W2126623367","https://openalex.org/W1495755158","https://openalex.org/W2041167939","https://openalex.org/W2106459246","https://openalex.org/W2134501463","https://openalex.org/W2611868346","https://openalex.org/W1857573607"],"abstract_inverted_index":{"We":[0,37],"study":[1],"continuous":[2],"speech":[3,65,70],"recognition":[4,66],"based":[5,41,82],"on":[6,42,68],"sub-word":[7],"units":[8,54],"found":[9],"in":[10],"an":[11],"unsupervised":[12],"fashion.":[13],"For":[14],"agglutinative":[15],"languages":[16],"like":[17],"Finnish,":[18],"traditional":[19],"word-based":[20],"n-gram":[21],"language":[22,57],"modeling":[23,58],"does":[24],"not":[25],"work":[26],"well":[27],"due":[28],"to":[29,48,86,98,107],"the":[30,43,74,87,91,101],"huge":[31],"number":[32],"of":[33],"different":[34],"word":[35,79,88,102],"forms.":[36],"use":[38],"a":[39],"method":[40],"Minimum":[44],"Description":[45],"Length":[46],"principle":[47],"split":[49],"words":[50],"statistically":[51],"into":[52],"subword":[53],"allowing":[55],"efficient":[56],"and":[59,64,80,100],"unlimited":[60],"vocabulary.":[61],"The":[62],"perplexity":[63],"experiments":[67],"Finnish":[69],"data":[71],"show":[72],"that":[73],"resulting":[75],"model":[76],"outperforms":[77],"both":[78],"syllable":[81],"trigram":[83,89],"models.":[84],"Compared":[85],"model,":[90],"out-of-vocabulary":[92],"rate":[93,104],"is":[94],"reduced":[95],"from":[96,105],"20%":[97],"0%":[99],"error":[103],"56%":[106],"32%.":[108]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
