{"id":"https://openalex.org/W2993166981","doi":"https://doi.org/10.1109/asru46091.2019.9003882","title":"A Multi Purpose and Large Scale Speech Corpus in Persian and English for Speaker and Speech Recognition: The Deepmine Database","display_name":"A Multi Purpose and Large Scale Speech Corpus in Persian and English for Speaker and Speech Recognition: The Deepmine Database","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2993166981","doi":"https://doi.org/10.1109/asru46091.2019.9003882","mag":"2993166981"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003882","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.03627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102720435","display_name":"Hossein Zeinali","orcid":"https://orcid.org/0000-0002-3789-8091"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hossein Zeinali","raw_affiliation_strings":["Sharif DeepMine Ltd., Tehran, Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sharif DeepMine Ltd., Tehran, Iran","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Faculty of IT, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of IT, IT4I Centre of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Honza Cernocky","raw_affiliation_strings":["Brno University of Technology, Faculty of IT, IT4I Centre of Excellence, Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Faculty of IT, IT4I Centre of Excellence, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5467,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72678183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"397","last_page":"402"},"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":0.9977999925613403,"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.7838913798332214},{"id":"https://openalex.org/keywords/persian","display_name":"Persian","score":0.6548408269882202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.620380163192749},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6141038537025452},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5785056352615356},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4943540096282959},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4853628873825073},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.47855836153030396},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46533384919166565},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.46114593744277954},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4534097909927368},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44418686628341675},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.30426025390625},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14659535884857178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7838913798332214},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.6548408269882202},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.620380163192749},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6141038537025452},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5785056352615356},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4943540096282959},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4853628873825073},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47855836153030396},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46533384919166565},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.46114593744277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4534097909927368},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44418686628341675},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30426025390625},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14659535884857178},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru46091.2019.9003882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003882","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.03627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.03627","pdf_url":"https://arxiv.org/pdf/1912.03627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"mag:2993166981","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1912.03627v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1912.03627","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.03627","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.03627","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.03627","pdf_url":"https://arxiv.org/pdf/1912.03627","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2993166981.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W4317849","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1996512145","https://openalex.org/W2114925438","https://openalex.org/W2298694059","https://openalex.org/W2398971481","https://openalex.org/W2505121225","https://openalex.org/W2514741789","https://openalex.org/W2515750888","https://openalex.org/W2606778926","https://openalex.org/W2612122134","https://openalex.org/W2726515241","https://openalex.org/W2805744305","https://openalex.org/W6631362777","https://openalex.org/W6697674961","https://openalex.org/W6712618806"],"related_works":["https://openalex.org/W2163859589","https://openalex.org/W2165340520","https://openalex.org/W1517747606","https://openalex.org/W2896558859","https://openalex.org/W3097649098","https://openalex.org/W2943945516","https://openalex.org/W2140011577","https://openalex.org/W131677052","https://openalex.org/W2156657359","https://openalex.org/W2093311764","https://openalex.org/W2593011301","https://openalex.org/W2034625425","https://openalex.org/W1544453077","https://openalex.org/W2925134954","https://openalex.org/W2096278748","https://openalex.org/W3138988259","https://openalex.org/W2215178201","https://openalex.org/W1526568841","https://openalex.org/W1968633115","https://openalex.org/W2091229953"],"abstract_inverted_index":{"DeepMine":[0],"is":[1,47],"a":[2,80],"speech":[3,24,43],"database":[4,54,65,98,144],"in":[5,55,66],"Persian":[6,23],"and":[7,12,16,33,61,68,86,129],"English":[8],"designed":[9],"to":[10,99],"build":[11],"evaluate":[13],"text-dependent,":[14],"text-prompted,":[15],"text-independent":[17,75],"speaker":[18,52,63,76,107,127],"verification,":[19,128],"as":[20,22,121,131,133],"well":[21,132],"recognition":[25],"systems.":[26],"It":[27,46,78],"contains":[28],"more":[29,38],"than":[30,39],"1850":[31],"speakers":[32],"540":[34],"thousand":[35],"recordings":[36],"overall,":[37],"480":[40],"hours":[41],"of":[42,83,96,106,114],"are":[44],"transcribed.":[45],"the":[48,57,69,97,112,143],"first":[49],"public":[50,59,71],"large-scale":[51],"verification":[53,64],"Persian,":[56],"largest":[58,70],"text-dependent":[60,126],"text-prompted":[62],"English,":[67],"evaluation":[72,91],"dataset":[73],"for":[74,93,101,125,147],"verification.":[77,108],"has":[79],"good":[81],"coverage":[82],"age,":[84],"gender,":[85],"accents.":[87],"We":[88,109,140],"provide":[89,111],"several":[90,115],"protocols":[92],"each":[94],"part":[95],"allow":[100],"research":[102],"on":[103],"different":[104],"aspects":[105],"also":[110],"results":[113],"experiments":[116],"that":[117,142],"can":[118,145],"be":[119],"considered":[120],"baselines:":[122],"HMM-based":[123,130],"i-vectors":[124],"state-of-the-art":[134],"deep":[135],"neural":[136],"network":[137],"based":[138],"ASR.":[139],"demonstrate":[141],"serve":[146],"training":[148],"robust":[149],"ASR":[150],"models.":[151]},"counts_by_year":[{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}