{"id":"https://openalex.org/W4387490264","doi":"https://doi.org/10.23919/spa59660.2023.10274438","title":"Augmented Transformer for Speech Detection in Adverse Acoustical Conditions","display_name":"Augmented Transformer for Speech Detection in Adverse Acoustical Conditions","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4387490264","doi":"https://doi.org/10.23919/spa59660.2023.10274438"},"language":"en","primary_location":{"id":"doi:10.23919/spa59660.2023.10274438","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/spa59660.2023.10274438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","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/A5086810650","display_name":"Lukasz Smietanka","orcid":"https://orcid.org/0000-0002-2038-2136"},"institutions":[{"id":"https://openalex.org/I155313962","display_name":"West Pomeranian University of Technology","ror":"https://ror.org/0596m7f19","country_code":"PL","type":"education","lineage":["https://openalex.org/I155313962"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Lukasz Smietanka","raw_affiliation_strings":["West Pomeranian University of Technology, Szczecin,Faculty of Computer Science and Information Technology,Szczecin,Poland","Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Szczecin, Szczecin, Poland"],"affiliations":[{"raw_affiliation_string":"West Pomeranian University of Technology, Szczecin,Faculty of Computer Science and Information Technology,Szczecin,Poland","institution_ids":["https://openalex.org/I155313962"]},{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Szczecin, Szczecin, Poland","institution_ids":["https://openalex.org/I155313962"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030519875","display_name":"Tomasz M\u0105ka","orcid":"https://orcid.org/0000-0001-5898-2201"},"institutions":[{"id":"https://openalex.org/I155313962","display_name":"West Pomeranian University of Technology","ror":"https://ror.org/0596m7f19","country_code":"PL","type":"education","lineage":["https://openalex.org/I155313962"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Maka","raw_affiliation_strings":["West Pomeranian University of Technology, Szczecin,Faculty of Computer Science and Information Technology,Szczecin,Poland","Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Szczecin, Szczecin, Poland"],"affiliations":[{"raw_affiliation_string":"West Pomeranian University of Technology, Szczecin,Faculty of Computer Science and Information Technology,Szczecin,Poland","institution_ids":["https://openalex.org/I155313962"]},{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, West Pomeranian University of Technology, Szczecin, Szczecin, Poland","institution_ids":["https://openalex.org/I155313962"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5086810650"],"corresponding_institution_ids":["https://openalex.org/I155313962"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13527387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.9987000226974487,"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/transformer","display_name":"Transformer","score":0.7162826061248779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6512985229492188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.645050048828125},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5126868486404419},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4085661768913269},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3912801146507263},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21862411499023438},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11912599205970764},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08568474650382996},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08325445652008057}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7162826061248779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6512985229492188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.645050048828125},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5126868486404419},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4085661768913269},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3912801146507263},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21862411499023438},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11912599205970764},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08568474650382996},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08325445652008057}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/spa59660.2023.10274438","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/spa59660.2023.10274438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2398020690","https://openalex.org/W2928746352","https://openalex.org/W2954930777","https://openalex.org/W2972861996","https://openalex.org/W2988392183","https://openalex.org/W3094502228","https://openalex.org/W3160071434","https://openalex.org/W3160747466","https://openalex.org/W3208743843","https://openalex.org/W4226149039","https://openalex.org/W4295312788","https://openalex.org/W4296068805","https://openalex.org/W4302011253","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6802609832","https://openalex.org/W6810763489"],"related_works":["https://openalex.org/W191108438","https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W249088392","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,39,64],"have":[4,17,65],"presented":[5],"a":[6,19,41],"study":[7],"of":[8,24,97],"speech":[9,51,91],"signal":[10],"detection":[11,92],"in":[12,53,74],"adverse":[13,61],"acoustic":[14,62],"conditions.":[15],"We":[16],"prepared":[18],"dedicated":[20],"dataset,":[21],"where":[22],"fragments":[23],"monologues":[25],"and":[26,79],"dialogues":[27],"were":[28],"mixed":[29],"with":[30,77,94],"various":[31],"background":[32],"noises":[33],"at":[34],"five":[35],"SNR":[36],"levels.":[37],"Then":[38],"used":[40],"vision":[42],"transformer":[43,76],"adapted":[44],"to":[45,48,59],"audio":[46,55],"signals":[47],"determine":[49],"the":[50,60,75,86,95,98],"regions":[52],"an":[54,67,71],"signal.":[56],"To":[57],"adapt":[58],"conditions,":[63],"added":[66],"augmentation":[68],"module":[69],"as":[70],"extra":[72],"head":[73],"low-pass":[78],"band-pass":[80],"filters.":[81],"As":[82],"conducted":[83],"experiments":[84],"show,":[85],"proposed":[87],"AugViT":[88],"architecture":[89],"improves":[90],"compared":[93],"accuracy":[96],"baseline":[99],"ViT":[100],"transformer.":[101]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
