{"id":"https://openalex.org/W4413368329","doi":"https://doi.org/10.1007/978-3-032-02548-7_25","title":"ParCzech4Speech: A New Speech Corpus Derived from\u00a0Czech Parliamentary Data","display_name":"ParCzech4Speech: A New Speech Corpus Derived from\u00a0Czech Parliamentary Data","publication_year":2025,"publication_date":"2025-08-21","ids":{"openalex":"https://openalex.org/W4413368329","doi":"https://doi.org/10.1007/978-3-032-02548-7_25"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-02548-7_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/978-3-032-02548-7_25","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045237474","display_name":"Vladislav Stankov","orcid":"https://orcid.org/0000-0002-2034-6485"},"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":true,"raw_author_name":"Vladislav Stankov","raw_affiliation_strings":["Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Malostransk\u00e9 N\u00e1m\u011bst\u00ed 25, 11800, Prague, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-2034-6485","affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Malostransk\u00e9 N\u00e1m\u011bst\u00ed 25, 11800, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079201049","display_name":"Maty\u00e1\u0161 Kopp","orcid":"https://orcid.org/0000-0001-7953-8783"},"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":"Maty\u00e1\u0161 Kopp","raw_affiliation_strings":["Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Malostransk\u00e9 N\u00e1m\u011bst\u00ed 25, 11800, Prague, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-7953-8783","affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Malostransk\u00e9 N\u00e1m\u011bst\u00ed 25, 11800, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077746237","display_name":"Ond\u0159ej Bojar","orcid":"https://orcid.org/0000-0002-0606-0050"},"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":"Ond\u0159ej Bojar","raw_affiliation_strings":["Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Malostransk\u00e9 N\u00e1m\u011bst\u00ed 25, 11800, Prague, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-0606-0050","affiliations":[{"raw_affiliation_string":"Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (\u00daFAL), Charles University, Malostransk\u00e9 N\u00e1m\u011bst\u00ed 25, 11800, Prague, Czechia","institution_ids":["https://openalex.org/I21250087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045237474"],"corresponding_institution_ids":["https://openalex.org/I21250087"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35582571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"308"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T12380","display_name":"Authorship Attribution and Profiling","score":0.996999979019165,"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":0.995199978351593,"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":0.9211080074310303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8565086126327515},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49531617760658264},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45709720253944397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136212468147278},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21398189663887024}],"concepts":[{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.9211080074310303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565086126327515},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49531617760658264},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45709720253944397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136212468147278},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21398189663887024},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-032-02548-7_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2509.06675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.06675","pdf_url":"https://arxiv.org/pdf/2509.06675","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-02548-7_25","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-02548-7_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2166637769","https://openalex.org/W2560674852","https://openalex.org/W2898879711","https://openalex.org/W2972359262","https://openalex.org/W3043783436","https://openalex.org/W3119308075","https://openalex.org/W3197925926","https://openalex.org/W4385822293","https://openalex.org/W4402672020","https://openalex.org/W4405843222","https://openalex.org/W4406417959","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1485297680","https://openalex.org/W2782410293","https://openalex.org/W305958151","https://openalex.org/W2724504120","https://openalex.org/W2614400517","https://openalex.org/W2939805521","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,24],"introduce":[1],"ParCzech4Speech":[2],"1.0,":[3],"a":[4,102,122],"processed":[5,41],"version":[6,62],"of":[7,29],"the":[8,18,26,30,35,57,115,131,135],"ParCzech":[9,58],"4.0":[10],"corpus,":[11],"targeted":[12],"at":[13],"speech":[14,60,83,86],"modeling":[15],"tasks":[16,88],"with":[17,34,42,67,89,134],"largest":[19],"variant":[20],"containing":[21],"2,695":[22],"h.":[23],"combined":[25],"sound":[27],"recordings":[28,39],"Czech":[31],"parliamentary":[32],"speeches":[33],"official":[36],"transcripts.":[37],"The":[38,71,126],"were":[40],"WhisperX":[43],"and":[44,85,100,118,137],"Wav2Vec":[45],"2.0":[46],"to":[47],"extract":[48],"automated":[49],"audio-text":[50],"alignment.":[51],"Our":[52],"processing":[53],"pipeline":[54],"improves":[55],"upon":[56],"3.0":[59],"recognition":[61,84],"by":[63],"extracting":[64],"more":[65],"data":[66],"higher":[68],"alignment":[69],"reliability.":[70],"dataset":[72,127],"is":[73,128],"offered":[74],"in":[75,130],"three":[76],"flexible":[77],"variants:":[78],"(1)":[79],"sentence-segmented":[80,136],"for":[81,104,108],"automatic":[82],"synthesis":[87],"clean":[90],"boundaries,":[91],"(2)":[92],"unsegmented":[93,138],"preserving":[94],"original":[95,116],"utterance":[96],"flow":[97],"across":[98],"sentences,":[99],"(3)":[101],"raw-alignment":[103],"further":[105],"custom":[106],"refinement":[107],"other":[109],"possible":[110],"tasks.":[111],"All":[112],"variants":[113,139],"maintain":[114],"metadata":[117],"are":[119],"released":[120],"under":[121],"permissive":[123],"CC-BY":[124],"license.":[125],"available":[129,141],"LINDAT":[132],"repository,":[133],"additionally":[140],"on":[142],"Hugging":[143],"Face.":[144]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
