{"id":"https://openalex.org/W1553630706","doi":"https://doi.org/10.21437/interspeech.2005-489","title":"Automatic transcription of Czech, Russian, and Slovak spontaneous speech in the MALACH project","display_name":"Automatic transcription of Czech, Russian, and Slovak spontaneous speech in the MALACH project","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W1553630706","doi":"https://doi.org/10.21437/interspeech.2005-489","mag":"1553630706"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-489","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5038146266","display_name":"Josef Psutka","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Josef Psutka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047784245","display_name":"Pavel Ircing","orcid":"https://orcid.org/0000-0001-6967-1687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavel Ircing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057873612","display_name":"Josef Psutka","orcid":"https://orcid.org/0000-0003-4761-1645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. V. Psutka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102738283","display_name":"Jan Haji\u010d","orcid":"https://orcid.org/0000-0002-3503-7730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Hajic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070594684","display_name":"Bill Byrne","orcid":"https://orcid.org/0000-0003-1896-4492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William J. Byrne","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089400821","display_name":"Ji\u0159\u00ed M\u00edrovsk\u00fd","orcid":"https://orcid.org/0000-0003-2741-1347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jir\u00ed M\u00edrovsk\u00fd","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5038146266"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4571,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.72889933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1349","last_page":"1352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9944999814033508,"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":0.9944999814033508,"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":0.9807000160217285,"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":0.9739999771118164,"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":0.968919038772583},{"id":"https://openalex.org/keywords/slovak","display_name":"Slovak","score":0.9559282064437866},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6000407338142395},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5519048571586609},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3730524182319641},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32969072461128235},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19145238399505615}],"concepts":[{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.968919038772583},{"id":"https://openalex.org/C2780102689","wikidata":"https://www.wikidata.org/wiki/Q9058","display_name":"Slovak","level":3,"score":0.9559282064437866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6000407338142395},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5519048571586609},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3730524182319641},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32969072461128235},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19145238399505615},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2005-489","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.422.3719","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.422.3719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://svr-www.eng.cam.ac.uk/~wjb31/ppubs/EUROSP05MALACHsub.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:326648","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/326648/","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":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1563905377","https://openalex.org/W1595275880","https://openalex.org/W2123973749","https://openalex.org/W2127923419"],"related_works":["https://openalex.org/W2284304823","https://openalex.org/W4213113242","https://openalex.org/W3121760094","https://openalex.org/W2167960140","https://openalex.org/W2213239863","https://openalex.org/W2572672654","https://openalex.org/W2025245434","https://openalex.org/W2396875643","https://openalex.org/W2592508765","https://openalex.org/W2611664171"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,23,26,70,92],"3.5-years":[4],"effort":[5],"put":[6],"into":[7,120],"building":[8],"LVCSR":[9],"systems":[10],"for":[11,73],"recognition":[12],"of":[13,16,22,31,39,62,69,91,100,111,124,126],"spontaneous":[14],"speech":[15,38],"Czech,":[17],"Russian,":[18],"and":[19,35,57,59],"Slovak":[20],"witnesses":[21],"Holocaust":[24],"in":[25],"MALACH":[27],"project.":[28],"For":[29],"processing":[30],"colloquial,":[32],"highly":[33],"emotional":[34],"heavily":[36],"accented":[37,60],"elderly":[40],"people":[41],"containing":[42],"many":[43],"non-speech":[44,55],"events":[45,56],"we":[46],"have":[47],"developed":[48],"techniques":[49],"that":[50],"very":[51],"effectively":[52],"handle":[53],"both":[54],"colloquial":[58],"variants":[61],"uttered":[63],"words.":[64],"Manual":[65],"transcripts":[66],"as":[67],"one":[68],"main":[71],"sources":[72],"language":[74],"modeling":[75],"were":[76],"automatically":[77],"\u201enormalized":[78],"\u201d":[79],"using":[80],"standardized":[81],"lexicon,":[82],"which":[83],"brought":[84],"about":[85],"2":[86],"to":[87,128],"3":[88,129],"%":[89],"reduction":[90],"word":[93],"error":[94],"rate":[95],"(WER).":[96],"The":[97],"subsequent":[98],"interpolation":[99],"such":[101],"LMs":[102],"with":[103],"models":[104],"built":[105],"from":[106,115],"an":[107,121],"additional":[108,122],"collection":[109],"(consisting":[110],"topically":[112],"selected":[113],"sentences":[114],"general":[116],"text":[117],"corpora)":[118],"resulted":[119],"improvement":[123],"performance":[125],"up":[127],"%.":[130],"1.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
