{"id":"https://openalex.org/W4406461923","doi":"https://doi.org/10.1109/slt61566.2024.10832202","title":"Exploring ASR-Based WAV2VEC2 for Automated Speech Disorder Assessment: Insights and Analysis","display_name":"Exploring ASR-Based WAV2VEC2 for Automated Speech Disorder Assessment: Insights and Analysis","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461923","doi":"https://doi.org/10.1109/slt61566.2024.10832202"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5101786594","display_name":"Tuan Anh Nguyen","orcid":"https://orcid.org/0000-0002-3415-6148"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Tuan Nguyen","raw_affiliation_strings":["Avignon Universit&#x00E9;"],"affiliations":[{"raw_affiliation_string":"Avignon Universit&#x00E9;","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018458807","display_name":"Corinne Fredouille","orcid":"https://orcid.org/0000-0002-0413-8950"},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Corinne Fredouille","raw_affiliation_strings":["Avignon Universit&#x00E9;"],"affiliations":[{"raw_affiliation_string":"Avignon Universit&#x00E9;","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065909163","display_name":"Alain Ghio","orcid":"https://orcid.org/0000-0001-7302-0799"},"institutions":[{"id":"https://openalex.org/I21491767","display_name":"Aix-Marseille Universit\u00e9","ror":"https://ror.org/035xkbk20","country_code":"FR","type":"education","lineage":["https://openalex.org/I21491767"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alain Ghio","raw_affiliation_strings":["Aix-Marseille Universit&#x00E9;"],"affiliations":[{"raw_affiliation_string":"Aix-Marseille Universit&#x00E9;","institution_ids":["https://openalex.org/I21491767"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011961771","display_name":"Mathieu Balaguer","orcid":"https://orcid.org/0000-0003-1311-4501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mathieu Balaguer","raw_affiliation_strings":["Universit&#x00E9; de Toulouse"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulouse","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066517969","display_name":"Virginie Woisard","orcid":"https://orcid.org/0000-0003-3895-2827"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Virginie Woisard","raw_affiliation_strings":["Universit&#x00E9; de Toulouse"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulouse","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101786594"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70889094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"975","last_page":"982"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.998199999332428,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9944999814033508,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9940999746322632,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6845542192459106},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42455971240997314},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40334445238113403}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6845542192459106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42455971240997314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40334445238113403}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":30,"referenced_works":["https://openalex.org/W184563473","https://openalex.org/W1994534629","https://openalex.org/W2045956438","https://openalex.org/W2131915909","https://openalex.org/W2187089797","https://openalex.org/W2520486982","https://openalex.org/W2616146347","https://openalex.org/W2914304175","https://openalex.org/W2970820321","https://openalex.org/W3016223211","https://openalex.org/W3036132020","https://openalex.org/W3167533889","https://openalex.org/W4206481149","https://openalex.org/W4212800565","https://openalex.org/W4224919926","https://openalex.org/W4226380987","https://openalex.org/W4249992252","https://openalex.org/W4287854494","https://openalex.org/W4293764955","https://openalex.org/W4294103325","https://openalex.org/W4296070196","https://openalex.org/W4297730150","https://openalex.org/W4375869259","https://openalex.org/W4387391827","https://openalex.org/W4391515560","https://openalex.org/W6745682157","https://openalex.org/W6752726010","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6862472266"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"With":[0],"the":[1,8,40,64,67,77],"rise":[2],"of":[3,63,80],"SSL":[4,106],"and":[5,25,32,71,91,103,107,124,133],"ASR":[6,41,69,108],"technologies,":[7],"Wav2Vec2":[9,44,109],"ASR-based":[10],"model":[11,68,83,131],"has":[12],"been":[13],"fine-tuned":[14],"for":[15,30,84,136],"automated":[16],"speech":[17,35,85],"disorder":[18],"quality":[19,86],"assessment":[20,48],"tasks,":[21],"yielding":[22],"impressive":[23],"results":[24],"setting":[26],"a":[27,56,96],"new":[28],"baseline":[29,82],"Head":[31],"Neck":[33],"Cancer":[34],"contexts.":[36],"This":[37,74],"demonstrates":[38],"that":[39],"dimension":[42,70],"from":[43],"closely":[45],"aligns":[46],"with":[47,59],"dimensions.":[49],"Despite":[50],"its":[51],"effectiveness,":[52],"this":[53,81],"system":[54],"remains":[55],"black":[57],"box":[58],"no":[60],"clear":[61],"interpretation":[62],"connection":[65],"between":[66],"clinical":[72],"assessments.":[73],"paper":[75],"presents":[76],"first":[78],"analysis":[79,98],"assessment,":[87],"focusing":[88],"on":[89,112],"intelligibility":[90],"severity":[92],"tasks.":[93],"We":[94],"conduct":[95],"layer-wise":[97],"to":[99,129],"identify":[100],"key":[101],"layers":[102],"compare":[104],"different":[105],"models":[110],"based":[111],"pretrained":[113],"data.":[114],"Additionally,":[115],"post-hoc":[116],"XAI":[117],"methods,":[118],"including":[119],"Canonical":[120],"Correlation":[121],"Analysis":[122],"(CCA)":[123],"visualization":[125],"techniques,":[126],"are":[127],"used":[128],"track":[130],"evolution":[132],"visualize":[134],"embeddings":[135],"enhanced":[137],"interpretability.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
