{"id":"https://openalex.org/W7118173671","doi":"https://doi.org/10.3390/info17010040","title":"Listen Closely: Self-Supervised Phoneme Tracking for Children\u2019s Reading Assessment","display_name":"Listen Closely: Self-Supervised Phoneme Tracking for Children\u2019s Reading Assessment","publication_year":2026,"publication_date":"2026-01-04","ids":{"openalex":"https://openalex.org/W7118173671","doi":"https://doi.org/10.3390/info17010040"},"language":"en","primary_location":{"id":"doi:10.3390/info17010040","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17010040","pdf_url":"https://www.mdpi.com/2078-2489/17/1/40/pdf?version=1767501605","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/2078-2489/17/1/40/pdf?version=1767501605","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121919738","display_name":"Philipp Ollmann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Philipp Ollmann","raw_affiliation_strings":["Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria","institution_ids":["https://openalex.org/I4210136249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033816218","display_name":"Erik Sonnleitner","orcid":"https://orcid.org/0000-0002-0646-782X"},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Erik Sonnleitner","raw_affiliation_strings":["Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria"],"raw_orcid":"https://orcid.org/0000-0002-0646-782X","affiliations":[{"raw_affiliation_string":"Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria","institution_ids":["https://openalex.org/I4210136249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008231044","display_name":"Marc Kurz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Marc Kurz","raw_affiliation_strings":["Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria"],"raw_orcid":"https://orcid.org/0000-0002-2437-0589","affiliations":[{"raw_affiliation_string":"Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria","institution_ids":["https://openalex.org/I4210136249"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090437690","display_name":"Jens Kr\u00f6sche","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Jens Kr\u00f6sche","raw_affiliation_strings":["Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria"],"raw_orcid":"https://orcid.org/0009-0000-2492-5647","affiliations":[{"raw_affiliation_string":"Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria","institution_ids":["https://openalex.org/I4210136249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121947759","display_name":"Stephan Selinger","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136249","display_name":"University of Applied Sciences Upper Austria","ror":"https://ror.org/03jqp6d56","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210136249"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Stephan Selinger","raw_affiliation_strings":["Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department for Smart and Interconnected Living, University of Applied Sciences Upper Austria, Softwarepark 11, 4232 Hagenberg, Austria","institution_ids":["https://openalex.org/I4210136249"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033816218"],"corresponding_institution_ids":["https://openalex.org/I4210136249"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03088533,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":"40","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.31869998574256897,"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":0.31869998574256897,"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/T10730","display_name":"Language Development and Disorders","score":0.20239999890327454,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.10350000113248825,"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/reading","display_name":"Reading (process)","score":0.5860999822616577},{"id":"https://openalex.org/keywords/reading-aloud","display_name":"Reading aloud","score":0.4984999895095825},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4596000015735626},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.45570001006126404},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.454800009727478},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.3856000006198883},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3675999939441681},{"id":"https://openalex.org/keywords/read-aloud","display_name":"Read aloud","score":0.3467000126838684},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7125999927520752},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5860999822616577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5831999778747559},{"id":"https://openalex.org/C2993756790","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading aloud","level":3,"score":0.4984999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4596000015735626},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.45570001006126404},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4406000077724457},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2993951753","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Read aloud","level":3,"score":0.3467000126838684},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C74672266","wikidata":"https://www.wikidata.org/wiki/Q815859","display_name":"Language acquisition","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2567000091075897},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info17010040","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17010040","pdf_url":"https://www.mdpi.com/2078-2489/17/1/40/pdf?version=1767501605","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:32d195e9475d44169352a96297ee5e2b","is_oa":true,"landing_page_url":"https://doaj.org/article/32d195e9475d44169352a96297ee5e2b","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,"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":"Information, Vol 17, Iss 1, p 40 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info17010040","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info17010040","pdf_url":"https://www.mdpi.com/2078-2489/17/1/40/pdf?version=1767501605","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":[{"id":"https://metadata.un.org/sdg/4","score":0.8960998058319092,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7118173671.pdf","grobid_xml":"https://content.openalex.org/works/W7118173671.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W141885233","https://openalex.org/W2125838338","https://openalex.org/W2128160875","https://openalex.org/W2889212027","https://openalex.org/W2936774411","https://openalex.org/W2979826702","https://openalex.org/W3135639106","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4200300291","https://openalex.org/W4291746033","https://openalex.org/W4296068806","https://openalex.org/W4382344827","https://openalex.org/W4385822587","https://openalex.org/W4402111442"],"related_works":[],"abstract_inverted_index":{"Reading":[0],"proficiency":[1],"in":[2,28,210],"early":[3],"childhood":[4],"is":[5,35,122,126],"crucial":[6],"for":[7,42,73,240],"academic":[8],"success":[9],"and":[10,15,55,167,176,183,201,221],"intellectual":[11],"development.":[12],"However,":[13],"more":[14,16],"children":[17,34,51],"are":[18,44],"struggling":[19],"with":[20,37,86,132],"reading.":[21],"According":[22],"to":[23,96,194],"the":[24,129,133,136,144,148,164,196,235],"last":[25],"PISA":[26],"study":[27],"Austria,":[29],"one":[30],"out":[31],"of":[32,90,103,135,159,198,219,227,237],"five":[33],"dealing":[36],"reading":[38,53,80],"difficulties.":[39],"The":[40,186,206],"reasons":[41],"this":[43,67,211],"diverse,":[45],"but":[46],"an":[47],"application":[48],"that":[49,77],"tracks":[50,78],"while":[52],"aloud":[54],"guides":[56],"them":[57],"when":[58,119],"they":[59],"experience":[60],"difficulties":[61],"could":[62],"offer":[63],"meaningful":[64],"help.":[65],"Therefore,":[66],"proposal":[68],"explores":[69],"a":[70,74,82,87,214,222],"prototyping":[71],"approach":[72],"core":[75],"component":[76],"children\u2019s":[79],"using":[81,190],"self-supervised":[83,238],"Wav2Vec2":[84],"model":[85,125,208],"limited":[88],"amount":[89],"data.":[91],"Self-supervised":[92],"learning":[93],"allows":[94],"models":[95,187,239],"learn":[97],"general":[98],"representations":[99],"from":[100,147],"large":[101],"amounts":[102],"unlabeled":[104],"audio,":[105],"which":[106,154],"can":[107],"then":[108],"be":[109],"fine-tuned":[110],"on":[111,128,203,229],"smaller,":[112],"task-specific":[113],"datasets,":[114],"making":[115],"it":[116],"especially":[117],"useful":[118],"labeled":[120],"data":[121,166,171,192,199],"limited.":[123],"Our":[124],"operating":[127],"phonetic":[130],"level":[131],"help":[134],"International":[137],"Phonetic":[138],"Alphabet":[139],"(IPA).":[140],"To":[141,162],"implement":[142],"this,":[143],"KidsTALC":[145],"dataset":[146],"Leibniz":[149],"University":[150],"Hannover":[151],"was":[152],"used,":[153],"contains":[155],"spontaneous":[156],"speech":[157,232],"recordings":[158],"German-speaking":[160],"children.":[161],"enhance":[163],"training":[165],"improve":[168],"robustness,":[169],"several":[170],"augmentation":[172],"techniques":[173],"were":[174,188],"applied":[175],"evaluated,":[177],"including":[178],"pitch":[179],"shifting,":[180,182],"formant":[181],"speed":[184],"variation.":[185],"trained":[189,209],"different":[191],"configurations":[193],"compare":[195],"effects":[197],"variety":[200],"quality":[202],"recognition":[204],"performance.":[205],"best":[207],"work":[212],"achieved":[213],"phoneme":[215],"error":[216,224],"rate":[217,225],"(PER)":[218],"14.3%":[220],"word":[223],"(WER)":[226],"31.6%":[228],"unseen":[230],"child":[231],"data,":[233],"demonstrating":[234],"potential":[236],"such":[241],"use":[242],"cases.":[243]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-05T00:00:00"}
