{"id":"https://openalex.org/W7148293918","doi":"https://doi.org/10.1109/asru65441.2025.11434680","title":"Joint ASR and Speech Attribute Prediction for Conversational Dysarthric Speech Analysis with Multimodal Language Models","display_name":"Joint ASR and Speech Attribute Prediction for Conversational Dysarthric Speech Analysis with Multimodal Language Models","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148293918","doi":"https://doi.org/10.1109/asru65441.2025.11434680"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132806056","display_name":"Dominik Wagner","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dominik Wagner","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132823985","display_name":"Ilja Baumann","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilja Baumann","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093764","display_name":"Natalie Engert","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Natalie Engert","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099312136","display_name":"Elmar N\u00f6th","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elmar N\u00f6th","raw_affiliation_strings":["FAU Erlangen-N&#x00FC;rnberg"],"affiliations":[{"raw_affiliation_string":"FAU Erlangen-N&#x00FC;rnberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053498662","display_name":"Korbinian Riedhammer","orcid":"https://orcid.org/0000-0003-3582-2154"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korbinian Riedhammer","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033302750","display_name":"Tobias Bocklet","orcid":"https://orcid.org/0009-0008-7780-8821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tobias Bocklet","raw_affiliation_strings":["Technische Hochschule N&#x00FC;rnberg"],"affiliations":[{"raw_affiliation_string":"Technische Hochschule N&#x00FC;rnberg","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5132806056"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.72566233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.8806999921798706,"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"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.8806999921798706,"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/T12418","display_name":"Respiratory and Cough-Related Research","score":0.02850000001490116,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.015599999576807022,"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/joint","display_name":"Joint (building)","score":0.7250000238418579},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.39879998564720154},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3562999963760376},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.3224000036716461},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.30709999799728394},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.2948000133037567}],"concepts":[{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7250000238418579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.645799994468689},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6154000163078308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4203999936580658},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3562999963760376},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.2948000133037567},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.2888999879360199},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434680","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434680","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W2064610785","https://openalex.org/W2075441619","https://openalex.org/W2170951778","https://openalex.org/W2293992264","https://openalex.org/W2396944218","https://openalex.org/W2508244509","https://openalex.org/W2888807255","https://openalex.org/W2907121074","https://openalex.org/W2936774411","https://openalex.org/W2964525587","https://openalex.org/W3091860345","https://openalex.org/W3097777922","https://openalex.org/W3127339759","https://openalex.org/W3145837385","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3210724237","https://openalex.org/W4297841331","https://openalex.org/W4297841747","https://openalex.org/W4297841798","https://openalex.org/W4297841875","https://openalex.org/W4321122916","https://openalex.org/W4372259808","https://openalex.org/W4383301707","https://openalex.org/W4383302399","https://openalex.org/W4384211370","https://openalex.org/W4385245566","https://openalex.org/W4386025707","https://openalex.org/W4387580450","https://openalex.org/W4388588536","https://openalex.org/W4388677733","https://openalex.org/W4388853939","https://openalex.org/W4389083111","https://openalex.org/W4389518760","https://openalex.org/W4390873312","https://openalex.org/W4392903087","https://openalex.org/W4393178509","https://openalex.org/W4400275735","https://openalex.org/W4400615995","https://openalex.org/W4400929850","https://openalex.org/W4401609199","https://openalex.org/W4402111790","https://openalex.org/W4402111804","https://openalex.org/W4402115955","https://openalex.org/W4402639795","https://openalex.org/W4402890137","https://openalex.org/W4407561026","https://openalex.org/W4408352300","https://openalex.org/W4408352349","https://openalex.org/W4408353544","https://openalex.org/W4415432852","https://openalex.org/W4415433214","https://openalex.org/W4415525138","https://openalex.org/W7131789502","https://openalex.org/W7133212838"],"related_works":[],"abstract_inverted_index":{"Dysarthric":[0],"speech":[1,115],"recognition":[2],"systems":[3],"often":[4],"focus":[5],"solely":[6],"on":[7,35,74],"transcription,":[8],"limiting":[9],"their":[10],"applicability":[11],"in":[12],"clinical":[13],"and":[14,24,50,71,109],"assistive":[15],"settings":[16],"where":[17],"assessments":[18],"of":[19,113],"perceptual":[20,51],"attributes":[21,70],"like":[22],"intelligibility":[23],"naturalness":[25],"are":[26],"essential.":[27],"We":[28],"propose":[29],"a":[30],"multimodal":[31],"conversational":[32],"framework":[33],"based":[34],"Phi-4-Multimodal":[36],"that":[37],"combines":[38],"ASR":[39,85,99],"with":[40],"attribute":[41],"rating":[42],"prediction,":[43],"enabling":[44],"users":[45],"to":[46,92],"query":[47],"both":[48],"transcriptions":[49],"characteristics":[52],"(e.g.":[53],"\u201cHow":[54],"intelligible":[55],"is":[56,72],"this":[57],"utterance?\u201d).":[58],"Our":[59],"multitask":[60],"model":[61],"adds":[62],"auxiliary":[63],"prediction":[64],"heads":[65],"for":[66,101],"five":[67],"clinically":[68],"relevant":[69],"trained":[73],"the":[75],"English":[76],"Speech":[77],"Accessibility":[78],"Project":[79],"dataset.":[80],"The":[81],"system":[82],"achieves":[83],"competitive":[84],"performance":[86,100],"while":[87],"delivering":[88],"attribute-level":[89],"feedback":[90],"comparable":[91],"specialized":[93],"classifiers.":[94],"Additional":[95],"experiments":[96],"show":[97],"improved":[98],"German":[102],"Parkinson\u2019s":[103],"speech,":[104],"indicating":[105],"preserved":[106],"multilingual":[107],"capabilities":[108],"partial":[110],"cross-lingual":[111],"transfer":[112],"dysarthric":[114],"patterns.":[116]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}
