{"id":"https://openalex.org/W2063655091","doi":"https://doi.org/10.1109/slt.2012.6424202","title":"Word segmentation through cross-lingual word-to-phoneme alignment","display_name":"Word segmentation through cross-lingual word-to-phoneme alignment","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2063655091","doi":"https://doi.org/10.1109/slt.2012.6424202","mag":"2063655091"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2012.6424202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5061001839","display_name":"Felix Stahlberg","orcid":"https://orcid.org/0000-0002-0430-5704"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Felix Stahlberg","raw_affiliation_strings":["Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany","Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany#TAB#","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019720894","display_name":"Tim Schlippe","orcid":"https://orcid.org/0000-0002-9462-8610"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Schlippe","raw_affiliation_strings":["Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany","Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany#TAB#","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064572063","display_name":"Stephan Vogel","orcid":"https://orcid.org/0000-0003-2630-4881"},"institutions":[{"id":"https://openalex.org/I92528248","display_name":"Qatar Foundation","ror":"https://ror.org/01cawbq05","country_code":"QA","type":"funder","lineage":["https://openalex.org/I92528248"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Stephan Vogel","raw_affiliation_strings":["Qatar Foundation, Qatar Computing Research Institute, Qatar","Qatar Computing Research Institute, Qatar Foundation, Qatar#TAB#"],"affiliations":[{"raw_affiliation_string":"Qatar Foundation, Qatar Computing Research Institute, Qatar","institution_ids":["https://openalex.org/I92528248"]},{"raw_affiliation_string":"Qatar Computing Research Institute, Qatar Foundation, Qatar#TAB#","institution_ids":["https://openalex.org/I92528248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058049725","display_name":"Tanja Schultz","orcid":"https://orcid.org/0000-0002-9809-7028"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tanja Schultz","raw_affiliation_strings":["Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany","Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Cognitive Systems Lab, Karlsruhe Institute of Technology (KIT), Germany#TAB#","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061001839"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":2.5688,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.90237778,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":null,"first_page":"85","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.8390433192253113},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7756507992744446},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7039910554885864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6759841442108154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6641875505447388},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6298810839653015},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.578906238079071},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.535930335521698},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5057892799377441},{"id":"https://openalex.org/keywords/speech-segmentation","display_name":"Speech segmentation","score":0.4996495246887207},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4995245933532715},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19626912474632263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8390433192253113},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7756507992744446},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7039910554885864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6759841442108154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6641875505447388},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6298810839653015},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.578906238079071},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.535930335521698},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5057892799377441},{"id":"https://openalex.org/C207030507","wikidata":"https://www.wikidata.org/wiki/Q2266173","display_name":"Speech segmentation","level":3,"score":0.4996495246887207},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4995245933532715},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19626912474632263},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2012.6424202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2012.6424202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W44482469","https://openalex.org/W60702959","https://openalex.org/W66627554","https://openalex.org/W192980855","https://openalex.org/W206967138","https://openalex.org/W1526974435","https://openalex.org/W1599002823","https://openalex.org/W1605961137","https://openalex.org/W1973923101","https://openalex.org/W1984672765","https://openalex.org/W2006969979","https://openalex.org/W2038698865","https://openalex.org/W2042143122","https://openalex.org/W2101281673","https://openalex.org/W2126449874","https://openalex.org/W2126953647","https://openalex.org/W2152150600","https://openalex.org/W2156985047","https://openalex.org/W2904250082","https://openalex.org/W3023540311","https://openalex.org/W4237976374","https://openalex.org/W4285719527","https://openalex.org/W4299513722","https://openalex.org/W4388277788","https://openalex.org/W6601887226","https://openalex.org/W6602682705","https://openalex.org/W6652311901","https://openalex.org/W6678998471","https://openalex.org/W6682679816"],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W4396644016","https://openalex.org/W2037894725","https://openalex.org/W2393940967","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557","https://openalex.org/W2115867364","https://openalex.org/W2115592387"],"abstract_inverted_index":{"We":[0],"present":[1],"our":[2],"new":[3],"alignment":[4,76,110],"model":[5],"Model":[6,72,114],"3P":[7,73],"for":[8,45,74],"cross-lingual":[9,33],"word-to-phoneme":[10],"alignment,":[11],"and":[12,80,107],"show":[13],"that":[14],"unsupervised":[15],"learning":[16],"of":[17,25,60,68],"word":[18,87],"segmentation":[19,31,88],"is":[20,28,35],"more":[21],"accurate":[22],"when":[23],"information":[24,34],"another":[26],"language":[27],"used.":[29],"Word":[30],"with":[32],"highly":[36],"relevant":[37],"to":[38,98,118],"bootstrap":[39],"pronunciation":[40],"dictionaries":[41],"from":[42],"audio":[43],"data":[44],"Automatic":[46],"Speech":[47],"Recognition,":[48],"bypass":[49],"the":[50,58,66,75,92,104],"written":[51],"form":[52],"in":[53,65,101],"Speech-to-Speech":[54],"Translation":[55],"or":[56],"build":[57],"vocabulary":[59],"an":[61],"unseen":[62],"language,":[63],"particularly":[64],"context":[67],"under-resourced":[69],"languages.":[70],"Using":[71],"between":[77],"English":[78],"words":[79],"Spanish":[81],"phonemes":[82],"outperforms":[83],"a":[84,108],"state-of-the-art":[85],"monolingual":[86],"approach":[89],"[1]":[90],"on":[91,103,112],"BTEC":[93],"corpus":[94],"[2]":[95],"by":[96,116],"up":[97,117],"42%":[99],"absolute":[100],"F-Score":[102],"phoneme":[105],"level":[106],"GIZA++":[109],"based":[111],"IBM":[113],"3":[115],"17%.":[119]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}