{"id":"https://openalex.org/W4401306437","doi":"https://doi.org/10.48550/arxiv.2407.21211","title":"Self-Supervised Models in Automatic Whispered Speech Recognition","display_name":"Self-Supervised Models in Automatic Whispered Speech Recognition","publication_year":2024,"publication_date":"2024-07-30","ids":{"openalex":"https://openalex.org/W4401306437","doi":"https://doi.org/10.48550/arxiv.2407.21211"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.21211","pdf_url":"http://arxiv.org/pdf/2407.21211","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2407.21211","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033221571","display_name":"Aref Farhadipour","orcid":"https://orcid.org/0000-0002-3447-4330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farhadipour, Aref","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059438009","display_name":"Homa Asadi","orcid":"https://orcid.org/0000-0003-1655-1336"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asadi, Homa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028554788","display_name":"Volker Dellwo","orcid":"https://orcid.org/0000-0002-8494-6025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dellwo, Volker","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9775,"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":0.9775,"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":[],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.744141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6379639},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42175114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40048236},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3384409},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.25277725}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.21211","pdf_url":"http://arxiv.org/pdf/2407.21211","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.21211","pdf_url":"http://arxiv.org/pdf/2407.21211","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2559837139","https://openalex.org/W2166690696","https://openalex.org/W2152158029","https://openalex.org/W2131711534","https://openalex.org/W2042327336","https://openalex.org/W2033914206","https://openalex.org/W2012540220","https://openalex.org/W1151175420"],"abstract_inverted_index":{"In":[0,125],"automatic":[1,28,42,161,173],"speech":[2,12,30,43,52,84,150,162,174,179],"recognition,":[3],"any":[4],"factor":[5],"that":[6],"alters":[7],"the":[8,18,33,37,60,87,94,107,127,142,153],"acoustic":[9,57,157],"properties":[10,58],"of":[11,62,80,120,137,144,155],"can":[13],"pose":[14],"a":[15,24,72,78,115,135],"challenge":[16],"to":[17,48,54],"system's":[19],"performance.":[20],"This":[21,165],"paper":[22,190],"presents":[23],"novel":[25],"approach":[26,146],"for":[27,159,177,188],"whispered":[29,51,81,123,149],"recognition":[31,44,163,175],"in":[32,97,147],"Irish":[34,100],"dialect":[35],"using":[36],"self-supervised":[38],"WavLM":[39,74],"model.":[40],"Conventional":[41],"systems":[45],"often":[46],"fail":[47],"accurately":[49],"recognise":[50],"due":[53],"its":[55,112],"distinct":[56],"and":[59,82,89,99,151,183],"scarcity":[61],"relevant":[63],"training":[64],"data.":[65],"To":[66],"address":[67],"this":[68,189],"challenge,":[69],"we":[70],"utilized":[71],"pre-trained":[73],"model,":[75],"fine-tuned":[76],"with":[77,106],"combination":[79],"normal":[83],"data":[85],"from":[86],"wTIMIT":[88],"CHAINS":[90],"datasets,":[91],"which":[92],"include":[93],"English":[95],"language":[96],"Singaporean":[98],"dialects,":[101],"respectively.":[102],"Our":[103],"baseline":[104],"evaluation":[105],"OpenAI":[108],"Whisper":[109],"model":[110],"highlighted":[111],"limitations,":[113],"achieving":[114,134],"Word":[116],"Error":[117],"Rate":[118],"(WER)":[119],"18.8%":[121],"on":[122],"speech.":[124],"contrast,":[126],"proposed":[128],"WavLM-based":[129],"system":[130],"significantly":[131],"improved":[132],"performance,":[133],"WER":[136],"9.22%.":[138],"These":[139],"results":[140],"demonstrate":[141],"efficacy":[143],"our":[145],"recognising":[148],"underscore":[152],"importance":[154],"tailored":[156],"modeling":[158],"robust":[160],"systems.":[164],"study":[166],"provides":[167],"valuable":[168],"insights":[169],"into":[170],"developing":[171],"effective":[172],"solutions":[176],"challenging":[178],"affected":[180],"by":[181],"whisper":[182],"dialect.":[184],"The":[185],"source":[186],"codes":[187],"are":[191],"freely":[192],"available.":[193]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4401306437","counts_by_year":[],"updated_date":"2024-12-15T13:53:14.611296","created_date":"2024-08-04"}