{"id":"https://openalex.org/W4306810718","doi":"https://doi.org/10.1145/3554364.3559112","title":"Analysis of transcription tools for Brazilian Portuguese with focus on disfluency detection","display_name":"Analysis of transcription tools for Brazilian Portuguese with focus on disfluency detection","publication_year":2022,"publication_date":"2022-10-17","ids":{"openalex":"https://openalex.org/W4306810718","doi":"https://doi.org/10.1145/3554364.3559112"},"language":"en","primary_location":{"id":"doi:10.1145/3554364.3559112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3554364.3559112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st Brazilian Symposium on Human Factors in Computing Systems","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/A5083016798","display_name":"Alana S. Luna","orcid":"https://orcid.org/0000-0002-4327-6002"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alana S. Luna","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, S\u00e3o Paulo, Brasil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, S\u00e3o Paulo, Brasil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043984374","display_name":"Ariane Machado\u2010Lima","orcid":"https://orcid.org/0000-0002-5719-338X"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ariane Machado-Lima","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054257245","display_name":"F\u00e1tima L. S. Nunes","orcid":"https://orcid.org/0000-0003-0040-0752"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"F\u00e1tima L. S. Nunes","raw_affiliation_strings":["Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade de S\u00e3o Paulo, S\u00e3o Paulo, Brasil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55687487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9962999820709229,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.995199978351593,"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":0.8079575896263123},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6808634996414185},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6370488405227661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5593264698982239},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5113889575004578},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4955848455429077},{"id":"https://openalex.org/keywords/portuguese","display_name":"Portuguese","score":0.47642001509666443},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4158293604850769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3354588747024536},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1711772382259369}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079575896263123},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6808634996414185},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6370488405227661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5593264698982239},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5113889575004578},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4955848455429077},{"id":"https://openalex.org/C35219183","wikidata":"https://www.wikidata.org/wiki/Q5146","display_name":"Portuguese","level":2,"score":0.47642001509666443},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4158293604850769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3354588747024536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1711772382259369},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3554364.3559112","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3554364.3559112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st Brazilian Symposium on Human Factors in Computing Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"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":29,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2154740140","https://openalex.org/W2158791054","https://openalex.org/W2294770573","https://openalex.org/W2406617219","https://openalex.org/W2596075132","https://openalex.org/W2735010905","https://openalex.org/W2754400659","https://openalex.org/W2765080642","https://openalex.org/W2784225896","https://openalex.org/W2806941616","https://openalex.org/W2811501128","https://openalex.org/W2888586235","https://openalex.org/W2889320445","https://openalex.org/W2893129065","https://openalex.org/W2901140781","https://openalex.org/W2964829415","https://openalex.org/W2972328063","https://openalex.org/W2978310466","https://openalex.org/W2979480035","https://openalex.org/W2992847832","https://openalex.org/W3015919780","https://openalex.org/W3016128928","https://openalex.org/W3116963205","https://openalex.org/W3127642913","https://openalex.org/W3197433369","https://openalex.org/W4200459702","https://openalex.org/W4205974282","https://openalex.org/W4230535091"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W2072507639","https://openalex.org/W4231814374","https://openalex.org/W2155964760","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Advancements":[0],"and":[1,52,69,136,162,182,193,195,200],"easier":[2],"access":[3],"to":[4,8,104,108,151],"technology":[5],"has":[6,24],"led":[7],"a":[9,26],"greater":[10],"demand":[11],"for":[12,29,39,134,179,184],"applications":[13,43],"whose":[14],"interaction":[15,87],"is":[16],"performed":[17],"through":[18,88],"voice":[19],"recognition,":[20],"since":[21],"multimedia":[22],"content":[23],"been":[25],"valuable":[27],"source":[28],"computational":[30],"analysis.":[31,54],"In":[32,97],"this":[33,95],"sense,":[34],"vocal":[35],"representations":[36],"are":[37],"extracted":[38],"various":[40],"purposes":[41],"in":[42,44,62,126,139,141],"several":[45],"areas":[46],"such":[47],"as":[48],"convenience,":[49],"accessibility,":[50],"security":[51],"sentiment":[53],"The":[55,164],"main":[56],"challenge":[57],"of":[58,65,72,100,112,120,144,155,177],"speech":[59],"recognition":[60],"lies":[61],"the":[63,70,84,109,113,130,142,153,169],"variability":[64],"speakers,":[66],"environments,":[67],"devices":[68],"presence":[71],"disfluencies":[73,101],"during":[74],"spoken":[75],"speech.":[76],"These":[77],"aspects":[78,106],"influence":[79],"transcription":[80,122],"tools,":[81,123],"essential":[82],"when":[83],"user":[85],"requires":[86],"voice,":[89],"aiming":[90],"at":[91],"producing":[92],"texts":[93],"from":[94],"interaction.":[96],"particular,":[98],"detection":[99],"can":[102],"help":[103],"identify":[105],"related":[107],"emotional":[110],"status":[111],"speaker.":[114],"This":[115],"work":[116],"presents":[117],"an":[118],"analysis":[119],"text":[121],"with":[124,172,191,197],"focus":[125],"disfluency":[127],"detection,":[128],"encompassing":[129],"metrics":[131],"most":[132],"used":[133,138],"evaluation":[135],"databases":[137],"evaluations":[140],"context":[143],"Brazilian":[145],"Portuguese.":[146],"An":[147],"experiment":[148],"was":[149],"conducted":[150],"evaluate":[152],"performance":[154,171],"three":[156],"tools":[157],"(IBM":[158],"Watson,":[159],"Google":[160,165],"Speech":[161,166],"Vosk).":[163],"tool":[167],"achieved":[168],"best":[170],"average":[173],"Word":[174],"Error":[175],"Rate":[176],"9.69%":[178],"fluent":[180],"sentences":[181],"17.15%":[183],"disfluent":[185],"sentences,":[186],"followed":[187],"by":[188],"IBM":[189],"Watson":[190],"11.86%":[192],"23.44%":[194],"Vosk":[196],"14.39":[198],"%":[199],"22.56%":[201],"respectively.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}