{"id":"https://openalex.org/W4403300428","doi":"https://doi.org/10.1007/s10772-024-10140-6","title":"Comparison of wav2vec 2.0 models on three speech processing tasks","display_name":"Comparison of wav2vec 2.0 models on three speech processing tasks","publication_year":2024,"publication_date":"2024-10-10","ids":{"openalex":"https://openalex.org/W4403300428","doi":"https://doi.org/10.1007/s10772-024-10140-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10772-024-10140-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10140-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10140-6.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10140-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050568080","display_name":"Marie Kune\u0161ov\u00e1","orcid":"https://orcid.org/0000-0002-7187-8481"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Marie Kune\u0161ov\u00e1","raw_affiliation_strings":["New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-7187-8481","affiliations":[{"raw_affiliation_string":"New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020627791","display_name":"Zbyn\u011bk Zaj\u00edc","orcid":"https://orcid.org/0000-0002-4153-6560"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Zbyn\u011bk Zaj\u00edc","raw_affiliation_strings":["New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-4153-6560","affiliations":[{"raw_affiliation_string":"New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082381758","display_name":"Lubo\u0161 \u0160m\u00eddl","orcid":"https://orcid.org/0000-0002-8169-2410"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lubo\u0161 \u0160m\u00eddl","raw_affiliation_strings":["New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia"],"raw_orcid":"https://orcid.org/0000-0002-8169-2410","affiliations":[{"raw_affiliation_string":"New Technologies for the Information Society and Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czechia","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","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 Karafi\u00e1t","raw_affiliation_strings":["Faculty of Information Technology, Brno University of Technology, Brno, Czechia"],"raw_orcid":"https://orcid.org/0000-0001-6474-8366","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Brno University of Technology, Brno, Czechia","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020627791","https://openalex.org/A5050568080"],"corresponding_institution_ids":["https://openalex.org/I92715842"],"apc_list":{"value":2780,"currency":"USD","value_usd":2780},"apc_paid":{"value":2780,"currency":"USD","value_usd":2780},"fwci":2.1547,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.8890854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":"4","first_page":"847","last_page":"859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9281597137451172},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6232736706733704},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39367204904556274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3252147436141968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9281597137451172},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6232736706733704},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39367204904556274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3252147436141968}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10772-024-10140-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10140-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10140-6.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10772-024-10140-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10772-024-10140-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10772-024-10140-6.pdf","source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Speech Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1761812275","display_name":null,"funder_award_id":"90254)","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"},{"id":"https://openalex.org/G4347180492","display_name":"Robust processing of recordings for operations and security","funder_award_id":"VJ01010108","funder_id":"https://openalex.org/F4320311333","funder_display_name":"Ministerstvo Vnitra \u010cesk\u00e9 Republiky"}],"funders":[{"id":"https://openalex.org/F4320310981","display_name":"Z\u00e1pado\u010desk\u00e1 Univerzita v Plzni","ror":"https://ror.org/040t43x18"},{"id":"https://openalex.org/F4320311333","display_name":"Ministerstvo Vnitra \u010cesk\u00e9 Republiky","ror":"https://ror.org/05w1nn565"},{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403300428.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1563939609","https://openalex.org/W1589339348","https://openalex.org/W2083751884","https://openalex.org/W2169264834","https://openalex.org/W2408468399","https://openalex.org/W2673722796","https://openalex.org/W2746241180","https://openalex.org/W2750259098","https://openalex.org/W2888082145","https://openalex.org/W2889256969","https://openalex.org/W2889408136","https://openalex.org/W2889496963","https://openalex.org/W2890825077","https://openalex.org/W2937501454","https://openalex.org/W2968071640","https://openalex.org/W2972449503","https://openalex.org/W2979826702","https://openalex.org/W3015678936","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3041561163","https://openalex.org/W3045742579","https://openalex.org/W3157070662","https://openalex.org/W3162770427","https://openalex.org/W3174136362","https://openalex.org/W3197580070","https://openalex.org/W3198429080","https://openalex.org/W3198482860","https://openalex.org/W3202370288","https://openalex.org/W4224927243","https://openalex.org/W4283712703","https://openalex.org/W4295936633","https://openalex.org/W4297841362","https://openalex.org/W4297841447","https://openalex.org/W4297841455","https://openalex.org/W4372344102","https://openalex.org/W4375869109","https://openalex.org/W4385823385","https://openalex.org/W4391892525","https://openalex.org/W4392114345","https://openalex.org/W6739901393","https://openalex.org/W6802591457","https://openalex.org/W6909330955","https://openalex.org/W6945130725"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Abstract":[0],"The":[1,21,45,70],"current":[2],"state-of-the-art":[3],"for":[4,41,48,177],"various":[5],"speech":[6,37,143,154],"processing":[7,144],"problems":[8],"is":[9,26,113,125],"a":[10,15,27,42,61,97,106,219],"sequence-to-sequence":[11],"model":[12,30],"based":[13],"on":[14,32,79,159,184,192],"self-attention":[16],"mechanism":[17],"known":[18],"as":[19,86],"transformer.":[20],"widely":[22],"used":[23,47,73,176],"wav2vec":[24,74,137,167],"2.0":[25,75,138,168],"self-supervised":[28],"transformer":[29,58],"pre-trained":[31],"large":[33],"amounts":[34],"of":[35,56,66,108,129],"unlabeled":[36],"and":[38,50,152,156,173,179],"then":[39],"fine-tuned":[40],"specific":[43],"task.":[44],"data":[46,82,103,175,186,195,206],"training":[49,68,194],"fine-tuning,":[51],"along":[52],"with":[53,170],"the":[54,57,87,119,126,188,198,212],"size":[55],"model,":[59],"play":[60],"crucial":[62],"role":[63],"in":[64,99,140],"both":[65],"these":[67],"steps.":[69],"most":[71],"commonly":[72],"models":[76,139,169],"are":[77,208],"trained":[78],"relatively":[80],"\u201cclean\u201d":[81],"from":[83,105,187,197],"sources":[84],"such":[85],"LibriSpeech":[88,199],"dataset,":[89],"but":[90],"we":[91,135,180],"can":[92],"expect":[93],"there":[94],"to":[95,211],"be":[96],"benefit":[98],"using":[100],"more":[101,209],"realistic":[102],"gathered":[104],"variety":[107],"acoustic":[109],"conditions.":[110],"However,":[111],"it":[112],"not":[114],"entirely":[115],"clear":[116],"how":[117],"big":[118],"difference":[120],"would":[121],"be.":[122],"Investigating":[123],"this":[124,133],"main":[127],"goal":[128],"our":[130],"article.":[131],"To":[132],"end,":[134],"utilize":[136],"three":[141],"fundamental":[142],"tasks:":[145],"speaker":[146],"change":[147],"detection,":[148,151,155],"voice":[149],"activity":[150],"overlapped":[153],"test":[157],"them":[158,182],"four":[160,166],"real":[161],"conversation":[162],"datasets.":[163],"We":[164],"compare":[165],"different":[171,174],"sizes":[172],"pre-training,":[178],"fine-tune":[181],"either":[183],"in-domain":[185],"same":[189],"dataset":[190],"or":[191],"artificial":[193],"created":[196],"corpus.":[200],"Our":[201],"results":[202],"suggest":[203],"that":[204,207],"richer":[205],"similar":[210],"task":[213],"domain":[214],"bring":[215],"better":[216],"performance":[217],"than":[218],"larger":[220],"model.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}