{"id":"https://openalex.org/W4415433901","doi":"https://doi.org/10.21437/interspeech.2025-658","title":"Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts","display_name":"Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433901","doi":"https://doi.org/10.21437/interspeech.2025-658"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-658","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.11079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079316816","display_name":"Lingyun Gao","orcid":"https://orcid.org/0000-0003-2509-9505"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lingyun Gao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046936545","display_name":"Cristian Tejedor-Garc\u0131\u0301a","orcid":"https://orcid.org/0000-0001-5395-0438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cristian Tejedor-Garcia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006678637","display_name":"Catia Cucchiarini","orcid":"https://orcid.org/0000-0001-5908-0824"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Catia Cucchiarini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019585114","display_name":"Helmer Strik","orcid":"https://orcid.org/0000-0003-1722-3465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helmer Strik","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079316816"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4617,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91856757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2850","last_page":"2854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9021000266075134,"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":0.9021000266075134,"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/mistake","display_name":"Mistake","score":0.9319000244140625},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.7972000241279602},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6890000104904175},{"id":"https://openalex.org/keywords/reading-aloud","display_name":"Reading aloud","score":0.6532999873161316},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4569000005722046},{"id":"https://openalex.org/keywords/read-aloud","display_name":"Read aloud","score":0.4025999903678894},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.3741999864578247}],"concepts":[{"id":"https://openalex.org/C2777179996","wikidata":"https://www.wikidata.org/wiki/Q911222","display_name":"Mistake","level":2,"score":0.9319000244140625},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.7972000241279602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7200999855995178},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6890000104904175},{"id":"https://openalex.org/C2993756790","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading aloud","level":3,"score":0.6532999873161316},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5519000291824341},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4535999894142151},{"id":"https://openalex.org/C2993951753","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Read aloud","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.34439998865127563},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C3018944925","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Reading level","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-658","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-658","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.11079","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11079","pdf_url":"https://arxiv.org/pdf/2506.11079","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.11079","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.11079","pdf_url":"https://arxiv.org/pdf/2506.11079","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"reading":[1,16,21,73,126],"aloud":[2],"evaluation":[3,22],"can":[4],"provide":[5],"valuable":[6],"support":[7],"to":[8,59,88,135],"teachers":[9],"by":[10],"enabling":[11],"more":[12],"efficient":[13],"scoring":[14],"of":[15,48,81,114,120],"exercises.":[17],"However,":[18],"research":[19],"on":[20],"systems":[23],"and":[24,37,51,84],"applications":[25],"remains":[26],"limited.":[27],"We":[28],"present":[29],"a":[30,109],"novel":[31],"multimodal":[32],"approach":[33],"that":[34],"leverages":[35],"audio":[36],"knowledge":[38],"from":[39,133],"text":[40],"resources.":[41],"In":[42],"particular,":[43],"we":[44],"explored":[45],"the":[46,79,89,117,130],"potential":[47],"using":[49],"Whisper":[50,83,91],"instruction-tuned":[52],"large":[53],"language":[54],"models":[55],"(LLMs)":[56],"with":[57,108],"prompts":[58],"improve":[60],"transcriptions":[61],"for":[62],"child":[63,105],"speech":[64],"recognition,":[65],"as":[66,68],"well":[67],"their":[69],"effectiveness":[70,80],"in":[71,103],"downstream":[72],"mistake":[74,127],"detection.":[75],"Our":[76],"results":[77],"demonstrate":[78],"prompting":[82,85],"LLM,":[86],"compared":[87],"baseline":[90,118],"model":[92],"without":[93],"prompting.":[94],"The":[95],"best":[96],"performing":[97],"system":[98],"achieved":[99],"state-of-the-art":[100],"recognition":[101],"performance":[102],"Dutch":[104],"read":[106],"speech,":[107],"word":[110],"error":[111],"rate":[112],"(WER)":[113],"5.1%,":[115],"improving":[116],"WER":[119],"9.4%.":[121],"Furthermore,":[122],"it":[123],"significantly":[124],"improved":[125],"detection,":[128],"increasing":[129],"F1":[131],"score":[132],"0.39":[134],"0.73.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-23T00:00:00"}