{"id":"https://openalex.org/W2738884019","doi":"https://doi.org/10.1109/sped.2017.7990428","title":"The SWARA speech corpus: A large parallel Romanian read speech dataset","display_name":"The SWARA speech corpus: A large parallel Romanian read speech dataset","publication_year":2017,"publication_date":"2017-07-01","ids":{"openalex":"https://openalex.org/W2738884019","doi":"https://doi.org/10.1109/sped.2017.7990428","mag":"2738884019"},"language":"en","primary_location":{"id":"doi:10.1109/sped.2017.7990428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2017.7990428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","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/A5018126799","display_name":"Adriana Stan","orcid":"https://orcid.org/0000-0003-2894-5770"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Adriana Stan","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112300577","display_name":"Florina Veronica Dinescu","orcid":null},"institutions":[{"id":"https://openalex.org/I208470662","display_name":"Iuliu Ha\u021bieganu University of Medicine and Pharmacy","ror":"https://ror.org/051h0cw83","country_code":"RO","type":"education","lineage":["https://openalex.org/I208470662"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Florina Dinescu","raw_affiliation_strings":["Department of Otorhinolaryngology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otorhinolaryngology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I208470662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018528559","display_name":"Cristina \u0162iple","orcid":"https://orcid.org/0000-0003-2158-6904"},"institutions":[{"id":"https://openalex.org/I208470662","display_name":"Iuliu Ha\u021bieganu University of Medicine and Pharmacy","ror":"https://ror.org/051h0cw83","country_code":"RO","type":"education","lineage":["https://openalex.org/I208470662"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Cristina Tiple","raw_affiliation_strings":["Department of Otorhinolaryngology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otorhinolaryngology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I208470662"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007706908","display_name":"Serban Meza","orcid":"https://orcid.org/0000-0002-9109-0659"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Serban Meza","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011275629","display_name":"Bogdan Orza","orcid":"https://orcid.org/0000-0002-0544-903X"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Bogdan Orza","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048119797","display_name":"Magdalena Chiril\u0103","orcid":"https://orcid.org/0000-0002-3771-6614"},"institutions":[{"id":"https://openalex.org/I208470662","display_name":"Iuliu Ha\u021bieganu University of Medicine and Pharmacy","ror":"https://ror.org/051h0cw83","country_code":"RO","type":"education","lineage":["https://openalex.org/I208470662"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Magdalena Chirila","raw_affiliation_strings":["Department of Otorhinolaryngology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Otorhinolaryngology, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I208470662"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038722127","display_name":"Mircea Giurgiu","orcid":"https://orcid.org/0009-0007-9789-6083"},"institutions":[{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mircea Giurgiu","raw_affiliation_strings":["Communications Department, Technical University of Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Communications Department, Technical University of Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8588,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.89216093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9975000023841858,"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/T12031","display_name":"Speech and dialogue systems","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8183473348617554},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7822647094726562},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.7064311504364014},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6721545457839966},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6533915400505066},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.646147608757019},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.612491250038147},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.506740152835846},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5035080313682556},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4832685589790344},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.41155171394348145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3924916982650757},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.15712544322013855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183473348617554},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7822647094726562},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.7064311504364014},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6721545457839966},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6533915400505066},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.646147608757019},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.612491250038147},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.506740152835846},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5035080313682556},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4832685589790344},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41155171394348145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3924916982650757},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.15712544322013855},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sped.2017.7990428","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sped.2017.7990428","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W80543058","https://openalex.org/W111992245","https://openalex.org/W1516533146","https://openalex.org/W2018286258","https://openalex.org/W2054665642","https://openalex.org/W2059167550","https://openalex.org/W2163925746","https://openalex.org/W2231075402","https://openalex.org/W2400063444","https://openalex.org/W2408737549","https://openalex.org/W2471520273","https://openalex.org/W2554080800","https://openalex.org/W2598638573","https://openalex.org/W6603264027","https://openalex.org/W6604569431","https://openalex.org/W6630961876","https://openalex.org/W6712610176","https://openalex.org/W6713742277"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793","https://openalex.org/W2349468610"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"one":[3],"of":[4,62,95,102,115,121],"the":[5,25,100,104,119],"largest":[6],"Romanian":[7],"speech":[8,21,65],"datasets":[9],"freely":[10],"available":[11],"for":[12],"both":[13],"academic":[14],"and":[15,49,77,88,106],"commercial":[16],"use.":[17],"The":[18,42,54,72],"dataset":[19],"comprises":[20],"data":[22,43,107],"recorded":[23,37],"over":[24,69,92],"last":[26],"year":[27],"from":[28],"12":[29],"speakers,":[30],"along":[31],"with":[32],"5":[33],"other":[34],"speakers":[35,73,87],"previously":[36],"in":[38,118],"a":[39,112],"separate":[40],"environment.":[41],"was":[44],"manually":[45],"segmented":[46],"at":[47,52],"utterance-level":[48],"semi-automatically":[50],"labelled":[51],"phone-level.":[53],"resulting":[55],"corpus":[56,117],"amounts":[57],"to":[58,85,91],"approximately":[59],"21":[60],"hours":[61,94],"high-quality":[63],"read":[64,74],"data,":[66],"split":[67],"into":[68],"19,000":[70],"utterances.":[71],"between":[75],"921":[76],"1493":[78],"utterances":[79,82],"each.":[80],"880":[81],"are":[83],"common":[84],"all":[86],"add":[89],"up":[90],"16":[93],"parallel":[96],"data.":[97],"We":[98],"present":[99],"steps":[101],"performing":[103],"recordings":[105],"segmentation,":[108],"as":[109,111],"well":[110],"first":[113],"use":[114],"this":[116],"context":[120],"synthetic":[122],"voice":[123],"development.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}