{"id":"https://openalex.org/W2296029621","doi":"https://doi.org/10.21437/interspeech.2011-787","title":"Rapid building of an ASR system for under-resourced languages based on multilingual unsupervised training","display_name":"Rapid building of an ASR system for under-resourced languages based on multilingual unsupervised training","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2296029621","doi":"https://doi.org/10.21437/interspeech.2011-787","mag":"2296029621"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-787","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"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":"Ngoc Thang Vu","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042378064","display_name":"Franziska Kraus","orcid":null},"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":"Franziska Kraus","raw_affiliation_strings":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]},{"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":["Karlsruhe Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020700841"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":9.6854,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.98063336,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9934999942779541,"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":0.7490847110748291},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.621314287185669},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5808069705963135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.531609058380127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3843647837638855},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3423546552658081},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.08505821228027344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490847110748291},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.621314287185669},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5808069705963135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.531609058380127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3843647837638855},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3423546552658081},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08505821228027344},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2011-787","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-787","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.2062","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.2062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://csl.ira.uka.de/fileadmin/media/publication_files/VuKrausSchultz_Interspeech2011.pdf","raw_type":"text"}],"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":14,"referenced_works":["https://openalex.org/W7869021","https://openalex.org/W55333121","https://openalex.org/W66627554","https://openalex.org/W198385923","https://openalex.org/W1571931074","https://openalex.org/W1993952617","https://openalex.org/W2033436836","https://openalex.org/W2106554350","https://openalex.org/W2111702745","https://openalex.org/W2128212935","https://openalex.org/W2129334286","https://openalex.org/W2133267619","https://openalex.org/W2164505566","https://openalex.org/W2612280934"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W4366179611","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"our":[3],"work":[4],"on":[5,13,72,157,164],"rapid":[6,170],"language":[7,122,141,171],"adaptation":[8,172],"of":[9,88,95,102,120,133,154,173],"acoustic":[10],"models":[11],"based":[12,71],"multilingual":[14,127,177],"cross-language":[15,67],"bootstrapping":[16],"and":[17,37,80,92,98,161],"unsupervised":[18,69,175],"training.":[19],"We":[20,82],"used":[21],"Automatic":[22],"Speech":[23],"Recognition":[24],"(ASR)":[25],"systems":[26,124],"in":[27,130,138],"the":[28,73,84,93,100,110,118,126,134,139,158,165],"six":[29],"source":[30,96,121],"languages":[31,97],"English,":[32],"French,":[33],"German,":[34],"Spanish,":[35],"Bulgarian":[36],"Polish":[38],"to":[39],"build":[40],"from":[41],"scratch":[42],"an":[43,48],"ASR":[44,123,136],"system":[45,137,147],"for":[46,125],"Vietnamese,":[47],"underresourced":[49],"language.":[50],"System":[51],"building":[52],"was":[53],"performed":[54],"without":[55],"using":[56],"any":[57],"transcribed":[58],"audio":[59],"data":[60],"by":[61,106],"applying":[62,107],"three":[63],"consecutive":[64],"steps,":[65],"i.e.":[66],"transfer,":[68],"training":[70],"\u201cmultilingual":[74,89,103],"A-stabil":[75,90,104],"\u201d":[76,91,105],"confidence":[77],"score":[78],"[1],":[79],"bootstrapping.":[81],"investigated":[83],"correlation":[85],"between":[86],"performance":[87,101,132],"number":[94],"improved":[99],"it":[108],"at":[109],"syllable":[111],"level.":[112],"Furthermore,":[113],"we":[114],"showed":[115],"that":[116],"increasing":[117],"amount":[119],"framework":[128],"results":[129],"better":[131],"final":[135,144],"target":[140],"Vietnamese.":[142],"The":[143],"Vietnamese":[145],"recognition":[146],"has":[148],"a":[149],"Syllable":[150],"Error":[151],"Rate":[152],"(SyllER)":[153],"16.8":[155],"%":[156,163],"development":[159],"set":[160],"16.1":[162],"evaluation":[166],"set.":[167],"Index":[168],"Terms:":[169],"ASR,":[174],"training,":[176],"A-Stabil":[178]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}