{"id":"https://openalex.org/W4415433214","doi":"https://doi.org/10.21437/interspeech.2025-1553","title":"Exploring Generative Error Correction for Dysarthric Speech Recognition","display_name":"Exploring Generative Error Correction for Dysarthric Speech Recognition","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433214","doi":"https://doi.org/10.21437/interspeech.2025-1553"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-1553","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1553","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":["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/A5078641012","display_name":"Moreno La Quatra","orcid":"https://orcid.org/0000-0001-8838-064X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moreno La Quatra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083365850","display_name":"Alkis Koudounas","orcid":"https://orcid.org/0000-0003-4386-0409"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alkis Koudounas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068293208","display_name":"Valerio Mario Salerno","orcid":"https://orcid.org/0000-0002-1048-7380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Valerio Mario Salerno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079659476","display_name":"Sabato Marco Siniscalchi","orcid":"https://orcid.org/0000-0002-0770-0507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sabato Marco Siniscalchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.9359222,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3284","last_page":"3288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.988099992275238,"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":0.988099992275238,"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/T10863","display_name":"Voice and Speech Disorders","score":0.975600004196167,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9635999798774719,"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/generative-grammar","display_name":"Generative grammar","score":0.6248000264167786},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5278000235557556},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.45010000467300415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3880000114440918},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3617999851703644},{"id":"https://openalex.org/keywords/speech-error","display_name":"Speech error","score":0.34929999709129333},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.34040001034736633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749000191688538},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7386999726295471},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6248000264167786},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5278000235557556},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C541956065","wikidata":"https://www.wikidata.org/wiki/Q2250680","display_name":"Speech error","level":3,"score":0.34929999709129333},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.34040001034736633},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-1553","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1553","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:iris.unipa.it:10447/694129","is_oa":false,"landing_page_url":"https://hdl.handle.net/10447/694129","pdf_url":null,"source":{"id":"https://openalex.org/S4306401065","display_name":"Nova Science Publishers (Nova Science Publishers, Inc.)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,28,68,74,97],"remarkable":[2],"progress":[3],"in":[4,87,105],"end-to-end":[5],"Automatic":[6],"Speech":[7,29,69],"Recognition":[8],"(ASR)":[9],"engines,":[10],"accurately":[11],"transcribing":[12],"dysarthric":[13,106],"speech":[14,39,107],"remains":[15],"a":[16,24],"major":[17],"challenge.":[18],"In":[19],"this":[20],"work,":[21],"we":[22,93],"proposed":[23],"two-stage":[25],"framework":[26],"for":[27],"Accessibility":[30,70],"Project":[31,71],"Challenge":[32],"at":[33],"INTERSPEECH":[34],"2025,":[35],"which":[36],"combines":[37],"cutting-edge":[38],"recognition":[40],"models":[41],"with":[42],"LLM-based":[43],"generative":[44],"error":[45],"correction":[46],"(GER).":[47],"We":[48],"assess":[49],"different":[50],"configurations":[51],"of":[52,76,100],"model":[53],"scales":[54],"and":[55,81,102],"training":[56],"strategies,":[57],"incorporating":[58],"specific":[59],"hypothesis":[60],"selection":[61],"to":[62],"improve":[63],"transcription":[64],"accuracy.":[65],"Experiments":[66],"on":[67,79],"dataset":[72],"demonstrate":[73],"strength":[75],"our":[77],"approach":[78],"structured":[80],"spontaneous":[82],"speech,":[83],"while":[84],"highlighting":[85],"challenges":[86],"single-word":[88],"recognition.":[89,108],"Through":[90],"comprehensive":[91],"analysis,":[92],"provide":[94],"insights":[95],"into":[96],"complementary":[98],"roles":[99],"acoustic":[101],"linguistic":[103],"modeling":[104]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}