{"id":"https://openalex.org/W13205","doi":"https://doi.org/10.21437/icslp.2002-438","title":"Design of an audio-visual speech corpus for the czech audio-visual speech synthesis","display_name":"Design of an audio-visual speech corpus for the czech audio-visual speech synthesis","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W13205","doi":"https://doi.org/10.21437/icslp.2002-438","mag":"13205"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5031485141","display_name":"Milo\u0161 \u017delezn\u00fd","orcid":"https://orcid.org/0000-0003-1695-4370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milos Zelezn\u00fd","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051877837","display_name":"Petr C\u00edsa\u0159","orcid":"https://orcid.org/0000-0002-5129-3208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petr C\u00edsar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084463145","display_name":"Zden\u011bk Kr\u0148oul","orcid":"https://orcid.org/0000-0002-2042-2898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zdenek Krnoul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5067770655","display_name":"Jan Nov\u00e1k","orcid":"https://orcid.org/0000-0003-2454-390X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Nov\u00e1k","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1941","last_page":"1944"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9907000064849854,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9907000064849854,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9761999845504761,"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/T11309","display_name":"Music and Audio Processing","score":0.9735999703407288,"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/audio-visual","display_name":"Audio visual","score":0.8325862884521484},{"id":"https://openalex.org/keywords/czech","display_name":"Czech","score":0.8056765198707581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7710186243057251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6774450540542603},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6483646035194397},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5712014436721802},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5322188138961792},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.47016069293022156},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.41365155577659607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41009536385536194},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38996732234954834},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3812400698661804},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.19871392846107483},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18673059344291687}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8325862884521484},{"id":"https://openalex.org/C2777842544","wikidata":"https://www.wikidata.org/wiki/Q9056","display_name":"Czech","level":2,"score":0.8056765198707581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7710186243057251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6774450540542603},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6483646035194397},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5712014436721802},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5322188138961792},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.47016069293022156},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.41365155577659607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41009536385536194},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38996732234954834},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3812400698661804},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.19871392846107483},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18673059344291687},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/icslp.2002-438","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W86048793","https://openalex.org/W1561167278","https://openalex.org/W1584320209","https://openalex.org/W1921940208","https://openalex.org/W2096518980","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1911859126","https://openalex.org/W4312668661","https://openalex.org/W3151376046","https://openalex.org/W3089379469","https://openalex.org/W2105439218","https://openalex.org/W430347950","https://openalex.org/W2355899496","https://openalex.org/W642007152","https://openalex.org/W2903652364","https://openalex.org/W2147630093"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}