{"id":"https://openalex.org/W2164505566","doi":"https://doi.org/10.21437/interspeech.2009-20","title":"Cross-language bootstrapping for unsupervised acoustic model training: rapid development of a Polish speech recognition system","display_name":"Cross-language bootstrapping for unsupervised acoustic model training: rapid development of a Polish speech recognition system","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W2164505566","doi":"https://doi.org/10.21437/interspeech.2009-20","mag":"2164505566"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5069730908","display_name":"Jonas L\u00f6\u00f6f","orcid":null},"institutions":[{"id":"https://openalex.org/I2799853480","display_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","ror":"https://ror.org/00k4h2615","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2799853480","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonas L\u00f6\u00f6f","raw_affiliation_strings":["-Computer Science Dept. RWTH Aachen University, Aachen, Germany","Lehrstuhl f\u00fcr Informatik"],"affiliations":[{"raw_affiliation_string":"-Computer Science Dept. RWTH Aachen University, Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik","institution_ids":["https://openalex.org/I2799853480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084597617","display_name":"Christian Gollan","orcid":null},"institutions":[{"id":"https://openalex.org/I2799853480","display_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","ror":"https://ror.org/00k4h2615","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2799853480","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Gollan","raw_affiliation_strings":["-Computer Science Dept. RWTH Aachen University, Aachen, Germany","Lehrstuhl f\u00fcr Informatik"],"affiliations":[{"raw_affiliation_string":"-Computer Science Dept. RWTH Aachen University, Aachen, Germany","institution_ids":[]},{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik","institution_ids":["https://openalex.org/I2799853480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I2799853480","display_name":"Schloss Dagstuhl \u2013 Leibniz Center for Informatics","ror":"https://ror.org/00k4h2615","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2799853480","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Lehrstuhl f\u00fcr Informatik","-Computer Science Dept. RWTH Aachen University, Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Lehrstuhl f\u00fcr Informatik","institution_ids":["https://openalex.org/I2799853480"]},{"raw_affiliation_string":"-Computer Science Dept. RWTH Aachen University, Aachen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069730908"],"corresponding_institution_ids":["https://openalex.org/I2799853480"],"apc_list":null,"apc_paid":null,"fwci":7.2266,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.9711711,"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":0.9997000098228455,"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/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/T10860","display_name":"Speech and Audio Processing","score":0.991100013256073,"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":0.9825999736785889,"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":0.8125555515289307},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.7977279424667358},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7721977829933167},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.7034732699394226},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.6717395782470703},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5441722273826599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5239565372467041},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5221017599105835},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.47768908739089966},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44699373841285706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3470401167869568},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27865859866142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125555515289307},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.7977279424667358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7721977829933167},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.7034732699394226},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.6717395782470703},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5441722273826599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5239565372467041},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5221017599105835},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.47768908739089966},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44699373841285706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3470401167869568},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27865859866142273},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2009-20","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-20","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.163.7997","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.163.7997","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/647/Loeoef--2009.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:125757","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/125757","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"10th annual conference of the International Speech Communication Association 2009 (INTERSPEECH 2009) : Brighton, United Kingdom, 6 - 10 September 2009. - Vol. 1<br/>10. Annual Conference of the International Speech Communication Association 2009, INTERSPEECH 2009, Brighton, UK, 2009-09-06 - 2009-09-10","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G3591549471","display_name":"Judicial Management by Digital Libraries Semantics","funder_award_id":"214306","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W7869021","https://openalex.org/W15497043","https://openalex.org/W23007503","https://openalex.org/W60369657","https://openalex.org/W144245531","https://openalex.org/W170072012","https://openalex.org/W199380068","https://openalex.org/W1484181928","https://openalex.org/W1553410761","https://openalex.org/W2056786202","https://openalex.org/W2110073835","https://openalex.org/W2129334286","https://openalex.org/W2143860348","https://openalex.org/W2150557579","https://openalex.org/W2161966221","https://openalex.org/W2171761326"],"related_works":["https://openalex.org/W2740630172","https://openalex.org/W2126322296","https://openalex.org/W2955724459","https://openalex.org/W2163537793","https://openalex.org/W2037769829","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W2402899696","https://openalex.org/W3021690593","https://openalex.org/W1955848339"],"abstract_inverted_index":{"This":[0,26,60],"paper":[1],"describes":[2],"the":[3,30,52,71,84,97,129,133,136,144],"rapid":[4],"development":[5,15],"of":[6,33,54,70,99,135,146],"a":[7,55],"Polish":[8],"language":[9],"speech":[10,91],"recognition":[11,67,92],"system.":[12],"The":[13,75],"system":[14,76],"was":[16,27,47,63,77,125,141],"performed":[17],"without":[18],"access":[19],"to":[20,49,96,127],"any":[21],"transcribed":[22],"acoustic":[23,40,45,130],"training":[24,107],"data.":[25,74],"achieved":[28,142],"through":[29,51,65],"combined":[31],"use":[32,53,98],"cross-language":[34],"bootstrapping":[35],"and":[36,68,79,87,120],"confidence":[37],"based":[38,104],"unsupervised":[39,100],"model":[41,46,62,101],"training.":[42,102],"A":[43],"Spanish":[44],"ported":[48],"Polish,":[50],"manually":[56],"constructed":[57],"phoneme":[58],"mapping.":[59],"initial":[61],"refined":[64],"iterative":[66],"retraining":[69],"untranscribed":[72],"audio":[73],"trained":[78],"evaluated":[80],"on":[81,143],"recordings":[82],"from":[83],"European":[85],"Parliament,":[86],"included":[88],"several":[89],"state-of-the-art":[90],"techniques":[93],"in":[94],"addition":[95],"Confidence":[103],"speaker":[105],"adaptive":[106],"using":[108],"features":[109],"space":[110],"transform":[111],"adaptation,":[112],"as":[113,115],"well":[114],"vocal":[116],"tract":[117],"length":[118],"normalization":[119],"maximum":[121],"likelihood":[122],"linear":[123],"regression,":[124],"used":[126],"refine":[128],"model.":[131],"Through":[132],"combination":[134],"different":[137],"techniques,":[138],"good":[139],"performance":[140],"domain":[145],"parliamentary":[147],"speeches.":[148]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
