{"id":"https://openalex.org/W4386931380","doi":"https://doi.org/10.3389/fdata.2023.1210559","title":"Benchmarking open source and paid services for speech to text: an analysis of quality and input variety","display_name":"Benchmarking open source and paid services for speech to text: an analysis of quality and input variety","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4386931380","doi":"https://doi.org/10.3389/fdata.2023.1210559","pmid":"https://pubmed.ncbi.nlm.nih.gov/37799510","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/10548127"},"language":"en","primary_location":{"id":"doi:10.3389/fdata.2023.1210559","doi":"https://doi.org/10.3389/fdata.2023.1210559","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2023.1210559","pdf_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1210559/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1210559/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057490206","display_name":"Antonino Ferraro","orcid":"https://orcid.org/0000-0002-1326-0325","observed_orcids":["https://orcid.org/0000-0002-1326-0325"]},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Antonino Ferraro","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069541151","display_name":"Antonio Galli","orcid":"https://orcid.org/0000-0001-9911-1517","observed_orcids":["https://orcid.org/0000-0001-9911-1517"]},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Antonio Galli","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038118094","display_name":"Valerio La Gatta","orcid":"https://orcid.org/0000-0002-5941-4684","observed_orcids":["https://orcid.org/0000-0002-5941-4684"]},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Valerio La Gatta","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022700280","display_name":"Marco Postiglione","orcid":"https://orcid.org/0000-0003-1470-8053","observed_orcids":["https://orcid.org/0000-0003-1470-8053"]},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Postiglione","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology, University of Naples \"Federico II\", Naples, Italy","institution_ids":["https://openalex.org/I71267560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5057490206"],"corresponding_institution_ids":["https://openalex.org/I71267560"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":2.1036,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.88833155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"1210559","last_page":"1210559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/speech-to-text","display_name":"speech-to-text","score":0.8899999856948853},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.7289999723434448},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.8560000061988831},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.9430000185966492},{"id":"https://openalex.org/keywords/audio-transcription","display_name":"audio transcription","score":0.3700000047683716},{"id":"https://openalex.org/keywords/tool-selection","display_name":"tool selection","score":0.4269999861717224}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8615785837173462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791165828704834},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6054772138595581},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.51971036195755},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5193784832954407},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5008926391601562},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.479995459318161},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.4571601450443268},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3654688596725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3529689311981201},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33613675832748413},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3219448924064636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3209555745124817},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.17848077416419983},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10526415705680847},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fdata.2023.1210559","doi":"https://doi.org/10.3389/fdata.2023.1210559","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2023.1210559","pdf_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1210559/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10548127","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10548127","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10548127/pdf/fdata-06-1210559.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Front Big Data","raw_type":"Text"},{"id":"pmid:37799510","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37799510","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in big data","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:0f900bff7a7f446da82e307b1e438550","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/0f900bff7a7f446da82e307b1e438550","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Big Data, Vol 6 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdata.2023.1210559","doi":"https://doi.org/10.3389/fdata.2023.1210559","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdata.2023.1210559","pdf_url":"https://www.frontiersin.org/articles/10.3389/fdata.2023.1210559/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210201220","display_name":"Frontiers in Big Data","issn_l":"2624-909X","issn":["2624-909X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","ki-jl-1","norway-1","poland-20","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386931380.pdf","grobid_xml":"https://content.openalex.org/works/W4386931380.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1922655562","https://openalex.org/W2045956438","https://openalex.org/W2250357346","https://openalex.org/W2524643686","https://openalex.org/W2551437525","https://openalex.org/W2798685342","https://openalex.org/W2799473636","https://openalex.org/W2884797218","https://openalex.org/W2982456909","https://openalex.org/W2995929068","https://openalex.org/W3036601975","https://openalex.org/W3086154751","https://openalex.org/W3100732527","https://openalex.org/W3139918052","https://openalex.org/W3167533889","https://openalex.org/W3169320628","https://openalex.org/W4319862283","https://openalex.org/W4385822293"],"related_works":["https://openalex.org/W2990859684","https://openalex.org/W4392007660","https://openalex.org/W7120201802","https://openalex.org/W3038681566","https://openalex.org/W4416529370","https://openalex.org/W4408132082","https://openalex.org/W3162534420","https://openalex.org/W4296079428","https://openalex.org/W3082922549","https://openalex.org/W3092312691"],"abstract_inverted_index":{"Introduction:":[0],"Speech":[1],"to":[2,32,145,186],"text":[3],"(STT)":[4],"technology":[5],"has":[6],"seen":[7],"increased":[8],"usage":[9],"in":[10,121],"recent":[11],"years":[12],"for":[13,25,91,109,203],"automating":[14],"transcription":[15],"of":[16,38,55,73,97,115,124,141,172,209],"spoken":[17],"language.":[18],"To":[19],"choose":[20],"the":[21,34,71,92,98,101,116,122,125,130,163,169,173,195,201,210],"most":[22],"suitable":[23],"tool":[24,153],"a":[26,52,63,106],"given":[27],"task,":[28],"it":[29],"is":[30],"essential":[31],"evaluate":[33],"performance":[35,69,123,137,154,191],"and":[36,42,58,87,165,183,207],"quality":[37],"both":[39],"open":[40,56,187],"source":[41,57,188],"paid":[43,59,177],"STT":[44,60,93,110,126,152,217],"services.":[45],"Methods:":[46],"In":[47],"this":[48],"paper,":[49],"we":[50],"conduct":[51],"benchmarking":[53],"study":[54,148,199],"services,":[61],"with":[62],"specific":[64,139,205],"focus":[65],"on":[66,129,138,194],"assessing":[67],"their":[68,190],"concerning":[70],"variety":[72],"input":[74,90,131,196],"text.":[75,132,197],"We":[76],"utilizes":[77],"ix":[78],"datasets":[79],"obtained":[80],"from":[81],"diverse":[82],"sources,":[83],"including":[84],"interviews,":[85],"lectures,":[86],"speeches,":[88],"as":[89,160,162],"tools.":[94],"The":[95,198],"evaluation":[96],"instruments":[99],"employs":[100],"Word":[102],"Error":[103],"Rate":[104],"(WER),":[105],"standard":[107],"metric":[108],"evaluation.":[111],"Results:":[112],"Our":[113,147],"analysis":[114],"results":[117],"demonstrates":[118],"significant":[119],"variations":[120],"tools":[127,134],"based":[128],"Certain":[133],"exhibit":[135],"superior":[136],"types":[140],"audio":[142,211],"samples":[143,212],"compared":[144,185],"others.":[146],"provides":[149],"insights":[150],"into":[151],"when":[155,213],"handling":[156],"substantial":[157],"data":[158],"volumes,":[159],"well":[161],"challenges":[164],"opportunities":[166],"posed":[167],"by":[168],"multimedia":[170],"nature":[171],"data.":[174],"Discussion:":[175],"Although":[176],"services":[178],"generally":[179],"demonstrate":[180],"better":[181],"accuracy":[182],"speed":[184],"alternatives,":[189],"remains":[192],"dependent":[193],"highlights":[200],"need":[202],"considering":[204],"requirements":[206],"characteristics":[208],"selecting":[214],"an":[215],"appropriate":[216],"tool.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-09-22T00:00:00"}
