{"id":"https://openalex.org/W2912021853","doi":"https://doi.org/10.1109/slt.2018.8639607","title":"Word Segmentation From Phoneme Sequences Based On Pitman-Yor Semi-Markov Model Exploiting Subword Information","display_name":"Word Segmentation From Phoneme Sequences Based On Pitman-Yor Semi-Markov Model Exploiting Subword Information","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912021853","doi":"https://doi.org/10.1109/slt.2018.8639607","mag":"2912021853"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5018403421","display_name":"Ryu Takeda","orcid":"https://orcid.org/0009-0007-0518-6245"},"institutions":[{"id":"https://openalex.org/I4210138169","display_name":"Osaka Research Institute of Industrial Science and Technology","ror":"https://ror.org/03r38cy24","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210138169"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryu Takeda","raw_affiliation_strings":["The Institute of Scientific and Industrial Research, Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Scientific and Industrial Research, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I4210138169","https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I4210138169","display_name":"Osaka Research Institute of Industrial Science and Technology","ror":"https://ror.org/03r38cy24","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210138169"]},{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["The Institute of Scientific and Industrial Research, Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Scientific and Industrial Research, Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I4210138169","https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander I. Rudnicky","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.169,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63206304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"12","issue":null,"first_page":"763","last_page":"770"},"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":0.9987999796867371,"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/T10860","display_name":"Speech and Audio Processing","score":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7676475048065186},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7539724111557007},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6626280546188354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6609908938407898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6425763964653015},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5274705290794373},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5078592896461487},{"id":"https://openalex.org/keywords/yoruba","display_name":"Yoruba","score":0.477060467004776},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4594905972480774},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.4469345510005951},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41970694065093994},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1498081088066101},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11747029423713684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7676475048065186},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7539724111557007},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6626280546188354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6609908938407898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6425763964653015},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5274705290794373},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5078592896461487},{"id":"https://openalex.org/C2777568999","wikidata":"https://www.wikidata.org/wiki/Q34311","display_name":"Yoruba","level":2,"score":0.477060467004776},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4594905972480774},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.4469345510005951},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41970694065093994},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1498081088066101},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11747029423713684},{"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/slt.2018.8639607","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639607","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W58893626","https://openalex.org/W266685121","https://openalex.org/W1539673959","https://openalex.org/W1810745899","https://openalex.org/W2005902041","https://openalex.org/W2076618452","https://openalex.org/W2100768664","https://openalex.org/W2104981903","https://openalex.org/W2107038463","https://openalex.org/W2107240889","https://openalex.org/W2122228338","https://openalex.org/W2126377586","https://openalex.org/W2127863960","https://openalex.org/W2130106985","https://openalex.org/W2140991203","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2166270474","https://openalex.org/W2166637769","https://openalex.org/W2186490579","https://openalex.org/W2251563156","https://openalex.org/W2294206829","https://openalex.org/W2295297373","https://openalex.org/W2394932179","https://openalex.org/W2398490608","https://openalex.org/W2468716020","https://openalex.org/W2733040285","https://openalex.org/W2747414243","https://openalex.org/W2785847546","https://openalex.org/W2962784628","https://openalex.org/W3034729383","https://openalex.org/W3098643042","https://openalex.org/W3102667484","https://openalex.org/W4247319331","https://openalex.org/W6601894380","https://openalex.org/W6602415096","https://openalex.org/W6609933929","https://openalex.org/W6651757226","https://openalex.org/W6675022971","https://openalex.org/W6676028815","https://openalex.org/W6679086047","https://openalex.org/W6679101406","https://openalex.org/W6684135220","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2084326697","https://openalex.org/W2194396582","https://openalex.org/W2027903142","https://openalex.org/W2082284720","https://openalex.org/W2116722627","https://openalex.org/W2537260108","https://openalex.org/W2354322608","https://openalex.org/W2379938888"],"abstract_inverted_index":{"Word":[0],"segmentation":[1,25],"from":[2],"phoneme":[3,45],"sequences":[4],"is":[5,21],"essential":[6],"to":[7,41,54,88],"identify":[8],"unknown":[9],"words":[10],"-of-vocabulary;":[11],"OOV)":[12],"in":[13,30,118],"spoken":[14],"dialogues.":[15],"The":[16,32],"Pitman-Yor":[17],"semi-Markov":[18],"model":[19,63,87],"(PYSMM)":[20],"used":[22],"for":[23,44,103,128],"word":[24],"that":[26,108],"handles":[27],"dynamic":[28],"increase":[29],"vocabularies.":[31],"obtained":[33,125],"vocabularies,":[34],"however,":[35],"still":[36],"include":[37],"meaningless":[38],"entries":[39],"due":[40],"insufficient":[42],"cues":[43],"sequences.":[46],"We":[47,59],"focus":[48],"here":[49],"on":[50,65],"using":[51,71,100],"subword":[52,66,69,101],"information":[53,102],"capture":[55],"patterns":[56],"as":[57],"\u201cwords.\u201d":[58],"propose":[60],"1)":[61,96],"a":[62,72,83],"based":[64],"N-gram":[67],"and":[68,75,85,106,116,130],"estimation":[70],"vocabulary":[73],"set,":[74],"2)":[76,107],"posterior":[77],"fusion":[78],"of":[79,82,91,99,120,123],"the":[80,97,112,121,124],"results":[81],"PYSMM":[84,113],"our":[86,109],"take":[89],"advantage":[90],"both.":[92],"Our":[93],"experiments":[94],"showed":[95],"potential":[98],"OOV":[104,126],"acquisition,":[105],"method":[110],"outperformed":[111],"by":[114],"1.53":[115],"1.07":[117],"terms":[119],"F-measure":[122],"set":[127],"English":[129],"Japanese":[131],"corpora,":[132],"respectively.":[133]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}