{"id":"https://openalex.org/W3127273935","doi":"https://doi.org/10.21437/iberspeech.2022-56","title":"BCN2BRNO: ASR System Fusion for Albayzin 2022 Speech to Text Challenge","display_name":"BCN2BRNO: ASR System Fusion for Albayzin 2022 Speech to Text Challenge","publication_year":2022,"publication_date":"2022-11-08","ids":{"openalex":"https://openalex.org/W3127273935","doi":"https://doi.org/10.21437/iberspeech.2022-56","mag":"3127273935"},"language":"en","primary_location":{"id":"doi:10.21437/iberspeech.2022-56","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-56","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"},"type":"preprint","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/A5031960713","display_name":"Martin Kocour","orcid":"https://orcid.org/0000-0003-4924-5124"},"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":true,"raw_author_name":"Martin Kocour","raw_affiliation_strings":["Brno University of Technology, Speech@FIT, IT4I CoE"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, IT4I CoE","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098185031","display_name":"Jahnavi Umesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jahnavi Umesh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065253688","display_name":"Martin Karafi\u00e1t","orcid":"https://orcid.org/0000-0001-6474-8366"},"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":"Martin Karafiat","raw_affiliation_strings":["Brno University of Technology, Speech@FIT, IT4I CoE"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, IT4I CoE","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041747927","display_name":"Jan G. \u0160vec","orcid":"https://orcid.org/0000-0001-5095-7415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00e1n \u0160vec","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489994","display_name":"Fernando L\u00f3pez","orcid":"https://orcid.org/0000-0002-7705-2250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fernando L\u00f3pez","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071561412","display_name":"Jordi Luque","orcid":"https://orcid.org/0000-0002-4507-4930"},"institutions":[{"id":"https://openalex.org/I4210134591","display_name":"Telefonica Research and Development","ror":"https://ror.org/03qgzzb04","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210097190","https://openalex.org/I4210134591"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jordi Luque","raw_affiliation_strings":["Telef\u00f3nica Research"],"affiliations":[{"raw_affiliation_string":"Telef\u00f3nica Research","institution_ids":["https://openalex.org/I4210134591"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056785364","display_name":"Karel Bene\u0161","orcid":"https://orcid.org/0000-0002-0805-1860"},"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":"Karel Bene\u0161","raw_affiliation_strings":["Brno University of Technology, Speech@FIT, IT4I CoE"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, IT4I CoE","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035162271","display_name":"Mireia D\u00edez","orcid":"https://orcid.org/0000-0001-7894-8377"},"institutions":[{"id":"https://openalex.org/I71999127","display_name":"Universitat de Barcelona","ror":"https://ror.org/021018s57","country_code":"ES","type":"education","lineage":["https://openalex.org/I71999127"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mireia Diez","raw_affiliation_strings":["Universitat de Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat de Barcelona","institution_ids":["https://openalex.org/I71999127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067611314","display_name":"Igor Sz\u00f6ke","orcid":"https://orcid.org/0000-0002-3288-3106"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Igor Szoke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045351360","display_name":"Karel Vesel\u00fd","orcid":"https://orcid.org/0000-0002-3568-7493"},"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":"Karel Vesel\u00fd","raw_affiliation_strings":["Brno University of Technology, Speech@FIT, IT4I CoE"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, IT4I CoE","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":[],"affiliations":[]},{"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 \u010cernock\u00fd","raw_affiliation_strings":["Brno University of Technology, Speech@FIT, IT4I CoE"],"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@FIT, IT4I CoE","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5031960713"],"corresponding_institution_ids":["https://openalex.org/I60587646"],"apc_list":null,"apc_paid":null,"fwci":0.58739646,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64626482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"280"},"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.7156676054000854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6307235956192017},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4881513714790344},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42797166109085083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3933486342430115},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2255803644657135},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.06305244565010071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156676054000854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6307235956192017},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4881513714790344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42797166109085083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3933486342430115},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2255803644657135},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.06305244565010071}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/iberspeech.2022-56","is_oa":false,"landing_page_url":"https://doi.org/10.21437/iberspeech.2022-56","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IberSPEECH 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1530760075","https://openalex.org/W1574170747","https://openalex.org/W1904457459","https://openalex.org/W2085628288","https://openalex.org/W2134800885","https://openalex.org/W2160650576","https://openalex.org/W2514966966","https://openalex.org/W2520160253","https://openalex.org/W2786234940","https://openalex.org/W2806470644","https://openalex.org/W2888867175","https://openalex.org/W2936774411","https://openalex.org/W2990594533","https://openalex.org/W3030437843","https://openalex.org/W3036367741","https://openalex.org/W3097945073","https://openalex.org/W3210615406","https://openalex.org/W4299911275"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"joint":[3],"effort":[4],"of":[5,12,36,56,91,101],"BUT":[6],"and":[7],"Telef\u00f3nica":[8],"Research":[9],"on":[10,24,40],"development":[11],"Automatic":[13],"Speech":[14],"Recognition":[15],"systems":[16,104],"for":[17,131],"Albayzin":[18,111],"2020":[19,112],"Challenge.We":[20],"compare":[21],"approaches":[22],"based":[23],"either":[25],"hybrid":[26,30],"or":[27],"end-to-end":[28,42],"models.In":[29],"modelling,":[31,43],"we":[32,44,87,122],"explore":[33],"the":[34,89],"impact":[35],"SpecAugment[1,":[37],"2]":[38],"layer":[39],"performance.For":[41],"used":[45,116],"a":[46,93],"convolutional":[47],"neural":[48],"network":[49],"with":[50,62],"gated":[51],"linear":[52],"units":[53],"(GLUs).The":[54],"performance":[55],"such":[57],"model":[58,67],"is":[59],"also":[60,123],"evaluated":[61],"an":[63],"additional":[64],"ngram":[65],"language":[66],"to":[68,78],"improve":[69],"word":[70],"error":[71],"rates.We":[72],"further":[73],"inspect":[74],"source":[75],"separation":[76],"methods":[77],"extract":[79],"speech":[80],"from":[81,114],"noisy":[82],"environment":[83],"(i.e.TV":[84],"shows).More":[85],"precisely,":[86],"assess":[88],"effect":[90],"using":[92],"neural-based":[94],"music":[95],"separator":[96],"named":[97],"Demucs":[98],"[3].A":[99],"fusion":[100],"our":[102,118,125],"best":[103],"achieved":[105],"23.33":[106],"%":[107],"WER":[108],"in":[109,117,127],"official":[110],"evaluations.Aside":[113],"techniques":[115],"final":[119],"submitted":[120],"systems,":[121],"describe":[124],"efforts":[126],"retrieving":[128],"high-quality":[129],"transcripts":[130],"training.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}