{"id":"https://openalex.org/W7139920834","doi":"https://doi.org/10.1016/j.procs.2026.01.064","title":"Self-Supervised Wav2Vec Representations Integrated with Transformers for Speech-to-Text Applications","display_name":"Self-Supervised Wav2Vec Representations Integrated with Transformers for Speech-to-Text Applications","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7139920834","doi":"https://doi.org/10.1016/j.procs.2026.01.064"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.01.064","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.064","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.01.064","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130243409","display_name":"Mohammed Hameed Ahmed AlTaei","orcid":null},"institutions":[{"id":"https://openalex.org/I45998257","display_name":"Sohar University","ror":"https://ror.org/02ftvf862","country_code":"OM","type":"education","lineage":["https://openalex.org/I45998257"]}],"countries":["OM"],"is_corresponding":true,"raw_author_name":"Mohammed Hameed Ahmed AlTaei","raw_affiliation_strings":["College of Computing and IT, University of Technology and Applied Sciences, Suhar, Oman"],"affiliations":[{"raw_affiliation_string":"College of Computing and IT, University of Technology and Applied Sciences, Suhar, Oman","institution_ids":["https://openalex.org/I45998257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130254182","display_name":"Mohamed Fadlalla Elhaj Hamad","orcid":null},"institutions":[{"id":"https://openalex.org/I45998257","display_name":"Sohar University","ror":"https://ror.org/02ftvf862","country_code":"OM","type":"education","lineage":["https://openalex.org/I45998257"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Mohamed Fadlalla Elhaj Hamad","raw_affiliation_strings":["College of Computing and IT, University of Technology and Applied Sciences, Suhar, Oman"],"affiliations":[{"raw_affiliation_string":"College of Computing and IT, University of Technology and Applied Sciences, Suhar, Oman","institution_ids":["https://openalex.org/I45998257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130219160","display_name":"Omar Al Hashimi","orcid":null},"institutions":[{"id":"https://openalex.org/I177463362","display_name":"University of West London","ror":"https://ror.org/03e5mzp60","country_code":"GB","type":"education","lineage":["https://openalex.org/I177463362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Omar Al Hashimi","raw_affiliation_strings":["School of Computing and Engineering, University of West London, London, UK"],"affiliations":[{"raw_affiliation_string":"School of Computing and Engineering, University of West London, London, UK","institution_ids":["https://openalex.org/I177463362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130221585","display_name":"Ameer Hakim Samawi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098257","display_name":"Iranshahr University","ror":"https://ror.org/00vp5ry21","country_code":"IR","type":"education","lineage":["https://openalex.org/I4210098257"]},{"id":"https://openalex.org/I70640408","display_name":"Tehran University of Medical Sciences","ror":"https://ror.org/01c4pz451","country_code":"IR","type":"education","lineage":["https://openalex.org/I70640408"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ameer Hakim Samawi","raw_affiliation_strings":["School of Nursing and Midwifery, Tehran University of Medical Sciences, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"School of Nursing and Midwifery, Tehran University of Medical Sciences, Tehran, Iran","institution_ids":["https://openalex.org/I70640408","https://openalex.org/I4210098257"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5130243409"],"corresponding_institution_ids":["https://openalex.org/I45998257"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93078013,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"275","issue":null,"first_page":"550","last_page":"557"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5216000080108643,"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":0.5216000080108643,"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":0.11010000109672546,"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":0.061000000685453415,"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/transformer","display_name":"Transformer","score":0.6370999813079834}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8834999799728394},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6370999813079834},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.3000999987125397},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2913999855518341},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.27559998631477356},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.01.064","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.064","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.01.064","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.01.064","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W3217109194","https://openalex.org/W4210475104","https://openalex.org/W4297478850","https://openalex.org/W4304013688","https://openalex.org/W4304692303","https://openalex.org/W4366198760","https://openalex.org/W4377030754","https://openalex.org/W4378227633","https://openalex.org/W4379618876","https://openalex.org/W4382068371","https://openalex.org/W4385067602","https://openalex.org/W4385441668","https://openalex.org/W4385701164","https://openalex.org/W4386755096","https://openalex.org/W4386825080","https://openalex.org/W4389379294","https://openalex.org/W4389937061","https://openalex.org/W4390056394","https://openalex.org/W4390362839","https://openalex.org/W4390501259","https://openalex.org/W4396601469","https://openalex.org/W4398185455","https://openalex.org/W4398199933","https://openalex.org/W4398199977","https://openalex.org/W4400733770","https://openalex.org/W4402254189","https://openalex.org/W4402568227","https://openalex.org/W4402877857","https://openalex.org/W4403104615","https://openalex.org/W4403111444","https://openalex.org/W4403938537","https://openalex.org/W4404489692","https://openalex.org/W4405062006","https://openalex.org/W4405838664","https://openalex.org/W4406125273","https://openalex.org/W4407040299","https://openalex.org/W4408744185","https://openalex.org/W4409269527","https://openalex.org/W4411661885","https://openalex.org/W4413191947"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"ASR":[1,34,126],"systems":[2,127],"often":[3],"struggle":[4],"with":[5,41],"low-resource":[6],"languages,":[7],"data":[8],"dependence,":[9],"and":[10,20,46,77,83,107,121,124,132,141,155],"robustness":[11],"in":[12,128],"noisy":[13],"or":[14],"domain-specific":[15],"environments.":[16],"Telemedicine,":[17],"clinical":[18,116],"recordkeeping,":[19],"multilingual":[21],"communication":[22],"depend":[23],"on":[24],"accurate":[25,88],"speech-to-text":[26,146],"systems.":[27],"This":[28,63],"work":[29],"introduces":[30],"Wav2Vec-RCNet,":[31],"a":[32,138],"novel":[33],"architecture":[35],"that":[36],"integrates":[37],"self-supervised":[38,149],"Wav2Vec":[39,55],"representations":[40,69],"recurrent":[42,152],"neural":[43],"networks":[44],"(RNNs)":[45],"combines":[47],"Cuckoo":[48,97],"Search-tuned":[49],"RNNs.":[50],"Contrastive":[51],"predictive":[52],"coding":[53],"lets":[54],"generate":[56],"high-dimensional":[57],"latent":[58],"embeddings":[59,79],"from":[60],"raw":[61],"audio.":[62],"is":[64],"possible":[65],"because":[66],"effective":[67],"feature":[68,150],"do":[70],"not":[71],"require":[72],"large":[73],"annotated":[74],"corpora.":[75],"LSTM":[76],"GRU":[78],"capture":[80],"the":[81],"temporal":[82],"sequential":[84],"connections":[85],"needed":[86],"for":[87,111,144],"voice":[89],"transcription.":[90],"The":[91],"L\u00e9vy":[92],"flight-based":[93],"search":[94],"dynamics":[95],"of":[96,130],"Search":[98],"optimise":[99],"learning":[100],"rates,":[101],"hidden":[102],"unit":[103],"dimensions,":[104],"dropout":[105],"probabilities,":[106],"attention":[108],"weight":[109],"distributions":[110],"optimum":[112],"performance.":[113],"Wav2Vec-RCNet":[114,136],"outperforms":[115],"benchmark":[117],"datasets,":[118,120],"multi-accent":[119],"conventional":[122],"supervised":[123],"hybrid":[125],"terms":[129],"word":[131],"character":[133],"error":[134],"rates.":[135],"constructs":[137],"scalable,":[139],"resource-efficient,":[140],"domain-adaptive":[142],"framework":[143],"real-world":[145],"applications,":[147],"leveraging":[148],"learning,":[151],"sequence":[153],"modeling,":[154],"metaheuristic-driven":[156],"optimization.":[157]},"counts_by_year":[],"updated_date":"2026-03-22T06:25:25.174409","created_date":"2026-03-21T00:00:00"}
