{"id":"https://openalex.org/W4321374970","doi":"https://doi.org/10.3390/info14020137","title":"Reconsidering Read and Spontaneous Speech: Causal Perspectives on the Generation of Training Data for Automatic Speech Recognition","display_name":"Reconsidering Read and Spontaneous Speech: Causal Perspectives on the Generation of Training Data for Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-02-19","ids":{"openalex":"https://openalex.org/W4321374970","doi":"https://doi.org/10.3390/info14020137"},"language":"en","primary_location":{"id":"doi:10.3390/info14020137","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14020137","pdf_url":"https://www.mdpi.com/2078-2489/14/2/137/pdf?version=1676887996","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/14/2/137/pdf?version=1676887996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052951000","display_name":"Philipp Gabler","orcid":"https://orcid.org/0000-0001-9424-4548"},"institutions":[{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Philipp Gabler","raw_affiliation_strings":["Area of Knowledge Discovery, Know-Center GmbH, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Area of Knowledge Discovery, Know-Center GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003584509","display_name":"Bernhard C. Geiger","orcid":"https://orcid.org/0000-0003-3257-743X"},"institutions":[{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Bernhard C. Geiger","raw_affiliation_strings":["Area of Knowledge Discovery, Know-Center GmbH, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Area of Knowledge Discovery, Know-Center GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027851634","display_name":"Barbara Schuppler","orcid":"https://orcid.org/0000-0003-4009-0832"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Barbara Schuppler","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014398832","display_name":"Roman Kern","orcid":"https://orcid.org/0000-0003-0202-6100"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210088621","display_name":"Know Center Research GmbH (Austria)","ror":"https://ror.org/004zhad81","country_code":"AT","type":"company","lineage":["https://openalex.org/I4210088621"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Roman Kern","raw_affiliation_strings":["Area of Knowledge Discovery, Know-Center GmbH, 8010 Graz, Austria","Institute of Interactive Systems and Data Science, Graz University of Technology, 8010 Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Area of Knowledge Discovery, Know-Center GmbH, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4210088621"]},{"raw_affiliation_string":"Institute of Interactive Systems and Data Science, Graz University of Technology, 8010 Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014398832"],"corresponding_institution_ids":["https://openalex.org/I4092182","https://openalex.org/I4210088621"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.2615,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90046828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"14","issue":"2","first_page":"137","last_page":"137"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7263035774230957},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6729973554611206},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5689098238945007},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5542560815811157},{"id":"https://openalex.org/keywords/causality","display_name":"Causality (physics)","score":0.5103499293327332},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.45795902609825134},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4532637596130371},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4524364471435547},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43629151582717896},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4265235960483551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3714224696159363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7263035774230957},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6729973554611206},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5689098238945007},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5542560815811157},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.5103499293327332},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.45795902609825134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4532637596130371},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4524364471435547},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43629151582717896},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4265235960483551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3714224696159363},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info14020137","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14020137","pdf_url":"https://www.mdpi.com/2078-2489/14/2/137/pdf?version=1676887996","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:67e31c2b20f74f2eb7370cba19e824cf","is_oa":true,"landing_page_url":"https://doaj.org/article/67e31c2b20f74f2eb7370cba19e824cf","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 14, Iss 2, p 137 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/14/2/137/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info14020137","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Information","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info14020137","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info14020137","pdf_url":"https://www.mdpi.com/2078-2489/14/2/137/pdf?version=1676887996","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6751696685","display_name":null,"funder_award_id":"P32700","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4321374970.pdf"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W90499676","https://openalex.org/W133097959","https://openalex.org/W566227102","https://openalex.org/W1494198834","https://openalex.org/W1512208174","https://openalex.org/W1516659296","https://openalex.org/W1800365115","https://openalex.org/W1833981795","https://openalex.org/W1977690962","https://openalex.org/W1994216910","https://openalex.org/W2002767771","https://openalex.org/W2021142154","https://openalex.org/W2040007958","https://openalex.org/W2052382192","https://openalex.org/W2055408826","https://openalex.org/W2073296933","https://openalex.org/W2080344481","https://openalex.org/W2091950237","https://openalex.org/W2096044236","https://openalex.org/W2099111195","https://openalex.org/W2105897558","https://openalex.org/W2124882279","https://openalex.org/W2127141656","https://openalex.org/W2141766660","https://openalex.org/W2143117649","https://openalex.org/W2143891888","https://openalex.org/W2146126871","https://openalex.org/W2146849125","https://openalex.org/W2156375095","https://openalex.org/W2165582599","https://openalex.org/W2166637769","https://openalex.org/W2171850596","https://openalex.org/W2178225550","https://openalex.org/W2193413348","https://openalex.org/W2225156818","https://openalex.org/W2295951612","https://openalex.org/W2336171935","https://openalex.org/W2395128905","https://openalex.org/W2396965719","https://openalex.org/W2514025902","https://openalex.org/W2606977969","https://openalex.org/W2727650337","https://openalex.org/W2737982026","https://openalex.org/W2754499401","https://openalex.org/W2790376986","https://openalex.org/W2792919287","https://openalex.org/W2889213362","https://openalex.org/W2899689163","https://openalex.org/W2903585907","https://openalex.org/W2912581782","https://openalex.org/W2971822821","https://openalex.org/W2973049979","https://openalex.org/W2973194065","https://openalex.org/W2995750307","https://openalex.org/W3003223579","https://openalex.org/W3044971416","https://openalex.org/W3095350795","https://openalex.org/W3100732527","https://openalex.org/W3101981467","https://openalex.org/W3106426924","https://openalex.org/W3124373176","https://openalex.org/W3127055158","https://openalex.org/W3131956450","https://openalex.org/W3132308259","https://openalex.org/W3133932964","https://openalex.org/W3160537436","https://openalex.org/W3163596720","https://openalex.org/W3166682767","https://openalex.org/W3198270883","https://openalex.org/W3198484663","https://openalex.org/W3204696009","https://openalex.org/W3204920203","https://openalex.org/W4243854160","https://openalex.org/W4252900093","https://openalex.org/W4255871753","https://openalex.org/W4287173589","https://openalex.org/W4288083802","https://openalex.org/W4291334102","https://openalex.org/W4306761536","https://openalex.org/W4312516176","https://openalex.org/W6630424030","https://openalex.org/W6630428593","https://openalex.org/W6631362777","https://openalex.org/W6637220762","https://openalex.org/W6677082149","https://openalex.org/W6679436768","https://openalex.org/W6755996536","https://openalex.org/W6795952400","https://openalex.org/W6879948123","https://openalex.org/W7030690028"],"related_works":["https://openalex.org/W2081494945","https://openalex.org/W2389053294","https://openalex.org/W1970893504","https://openalex.org/W4312071518","https://openalex.org/W2901208600","https://openalex.org/W1677090476","https://openalex.org/W830525666","https://openalex.org/W2574301230","https://openalex.org/W1547624382","https://openalex.org/W4320159092"],"abstract_inverted_index":{"Superficially,":[0],"read":[1,55,120],"and":[2,23,43,99,109,121,124,145,169,195],"spontaneous":[3,27,70,122],"speech\u2014the":[4],"two":[5],"main":[6],"kinds":[7,40],"of":[8,21,41,64,92,119,143,160,163,186],"training":[9,110],"data":[10,116,135,164],"for":[11,32,54],"automatic":[12,96],"speech":[13,28,97,123,173,189],"recognition\u2014appear":[14],"as":[15,102],"complementary,":[16],"but":[17,45],"are":[18],"equal:":[19],"pairs":[20],"texts":[22],"acoustic":[24],"signals.":[25],"Yet,":[26],"is":[29,35,47,60,74],"typically":[30],"harder":[31],"recognition.":[33],"This":[34],"usually":[36],"explained":[37],"by":[38,62,87,137],"different":[39],"variation":[42],"noise,":[44],"there":[46],"a":[48,77,89,103,129,179],"more":[49],"fundamental":[50],"deviation":[51],"at":[52],"play:":[53],"speech,":[56,71],"the":[57,65,72,115,126,141,154,158,161,184],"audio":[58],"signal":[59],"produced":[61],"recitation":[63],"given":[66,78],"text,":[67],"whereas":[68],"in":[69,188],"text":[73],"transcribed":[75],"from":[76,128,153],"signal.":[79],"In":[80],"this":[81,85],"review,":[82],"we":[83,132,176],"embrace":[84],"difference":[86],"presenting":[88],"first":[90],"introduction":[91],"causal":[93,130,180],"reasoning":[94],"into":[95],"recognition,":[98],"describing":[100],"causality":[101,155],"tool":[104],"to":[105,172],"study":[106],"speaking":[107],"styles":[108],"data.":[111,174],"After":[112],"breaking":[113],"down":[114],"generation":[117,136,165],"processes":[118],"analysing":[125],"domain":[127],"perspective,":[131],"highlight":[133],"how":[134,150,178],"annotation":[138],"must":[139],"affect":[140],"interpretation":[142],"inference":[144],"performance.":[146],"Our":[147],"work":[148],"discusses":[149],"various":[151],"results":[152],"literature":[156],"regarding":[157,191],"impact":[159],"direction":[162],"mechanisms":[166],"on":[167],"learning":[168],"prediction":[170],"apply":[171],"Finally,":[175],"argue":[177],"perspective":[181],"can":[182],"support":[183],"understanding":[185],"models":[187],"processing":[190],"their":[192],"behaviour,":[193],"capabilities,":[194],"limitations.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}