{"id":"https://openalex.org/W1563905377","doi":"https://doi.org/10.21437/eurospeech.2003-551","title":"Large vocabulary ASR for spontaneous czech in the MALACH project","display_name":"Large vocabulary ASR for spontaneous czech in the MALACH project","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1563905377","doi":"https://doi.org/10.21437/eurospeech.2003-551","mag":"1563905377"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-551","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-551","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/A5057873612","display_name":"Josef Psutka","orcid":"https://orcid.org/0000-0003-4761-1645"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Josef Psutka","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047784245","display_name":"Pavel Ircing","orcid":"https://orcid.org/0000-0001-6967-1687"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Pavel Ircing","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057873612","display_name":"Josef Psutka","orcid":"https://orcid.org/0000-0003-4761-1645"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"J.V. Psutka","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019022614","display_name":"Vlasta Radov\u00e1","orcid":"https://orcid.org/0000-0002-3258-8430"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Vlasta Radova","raw_affiliation_strings":["#N#University of West Bohemia#N#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N#University of West Bohemia#N#","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":null,"display_name":"William J. Byrne","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William J. Byrne","raw_affiliation_strings":["Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102738283","display_name":"Jan Haji\u010d","orcid":"https://orcid.org/0000-0002-3503-7730"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Hajic","raw_affiliation_strings":["Charles University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University in Prague","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089400821","display_name":"Ji\u0159\u00ed M\u00edrovsk\u00fd","orcid":"https://orcid.org/0000-0003-2741-1347"},"institutions":[{"id":"https://openalex.org/I21250087","display_name":"Charles University","ror":"https://ror.org/024d6js02","country_code":"CZ","type":"education","lineage":["https://openalex.org/I21250087"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jiri Mirovsky","raw_affiliation_strings":["Charles University in Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles University in Prague","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023304742","display_name":"Samuel Gustman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Gustman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1821","last_page":"1824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9532999992370605,"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/czech","display_name":"Czech","score":0.906260073184967},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.851821780204773},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7215401530265808},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6041334867477417},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.589647114276886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5845447182655334},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5551326274871826},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5027434825897217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49542272090911865},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.439339280128479},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43819862604141235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4304197132587433},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.31461435556411743}],"concepts":[{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.906260073184967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.851821780204773},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7215401530265808},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6041334867477417},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.589647114276886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5845447182655334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5551326274871826},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5027434825897217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49542272090911865},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.439339280128479},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43819862604141235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4304197132587433},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.31461435556411743},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/eurospeech.2003-551","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-551","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:10.1.1.128.2605","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.128.2605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://malach.umiacs.umd.edu/pubs/malachczeurosp03.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:327456","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/327456/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W139293362","https://openalex.org/W1573622913","https://openalex.org/W1631260214","https://openalex.org/W2103584254","https://openalex.org/W2155388323","https://openalex.org/W2327996191"],"related_works":["https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340","https://openalex.org/W1494910745"],"abstract_inverted_index":{"This":[0,23],"paper":[1],"describes":[2],"LVCSR":[3],"research":[4],"into":[5],"the":[6,14,31,38,41,50,53,67,75,116],"automatic":[7],"transcription":[8],"of":[9,40,52,77,96,119],"spontaneous":[10,92],"Czech":[11,78],"speech":[12,57,107],"in":[13,55,69,141,144],"MALACH":[15],"(Multilingual":[16],"Access":[17],"to":[18,26,30],"Large":[19],"Spoken":[20],"Archives)":[21],"project.":[22],"project":[24],"attempts":[25],"provide":[27],"improved":[28],"access":[29],"large":[32,136],"multilingual":[33],"spoken":[34],"archives":[35],"collected":[36],"by":[37,48,101],"Survivors":[39],"Shoah":[42],"Visual":[43],"History":[44],"Foundation":[45],"(VHF)":[46],"(www.vhf.org)":[47],"advancing":[49],"state":[51],"art":[54],"automated":[56],"recognition.":[58],"We":[59],"describe":[60],"a":[61,80,135],"baseline":[62],"ASR":[63],"system":[64],"and":[65,91,105],"discuss":[66],"problems":[68],"language":[70,83,121],"modeling":[71],"that":[72,84],"arise":[73],"from":[74,134],"nature":[76],"as":[79],"highly":[81],"inflectional":[82],"also":[85],"exhibits":[86],"diglossia":[87],"between":[88,112],"its":[89],"written":[90],"forms.":[93],"The":[94],"difficulties":[95],"this":[97],"task":[98],"are":[99],"compounded":[100],"heavily":[102],"accented,":[103],"emotional":[104],"disfluent":[106],"along":[108],"with":[109],"frequent":[110],"switching":[111],"languages.":[113],"To":[114],"overcome":[115],"limited":[117],"amount":[118],"relevant":[120],"model":[122],"data":[123],"we":[124],"use":[125],"statistical":[126],"techniques":[127],"for":[128],"selecting":[129],"an":[130],"appropriate":[131],"training":[132],"corpus":[133],"unstructured":[137],"text":[138],"collection":[139],"resulting":[140],"significant":[142],"reductions":[143],"word":[145],"error":[146],"rate.":[147],"1.":[148]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
