{"id":"https://openalex.org/W4391021532","doi":"https://doi.org/10.1109/asru57964.2023.10389789","title":"Detecting Speech Abnormalities With a Perceiver-Based Sequence Classifier that Leverages a Universal Speech Model","display_name":"Detecting Speech Abnormalities With a Perceiver-Based Sequence Classifier that Leverages a Universal Speech Model","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021532","doi":"https://doi.org/10.1109/asru57964.2023.10389789"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389789","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025419994","display_name":"Izhak Shafran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Izhak Shafran","raw_affiliation_strings":["Google DeepMind"],"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093115845","display_name":"Alex Ottenwess","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Ottenwess","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005285557","display_name":"Joseph R. Duffy","orcid":"https://orcid.org/0000-0001-8206-3432"},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph R. Jr Duffy","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031615915","display_name":"Rene L. Utianski","orcid":"https://orcid.org/0000-0001-9519-1302"},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rene L. Utianski","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069272448","display_name":"Leland R Barnard","orcid":"https://orcid.org/0000-0003-1569-9312"},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leland R. Barnard","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017176841","display_name":"John L. Stricker","orcid":null},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John L. Stricker","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036223666","display_name":"Daniela A. Wiepert","orcid":"https://orcid.org/0000-0002-6076-1712"},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniela Wiepert","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063489595","display_name":"David T. Jones","orcid":"https://orcid.org/0000-0002-4807-9833"},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David T. Jones","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046855704","display_name":"Hugo Botha","orcid":"https://orcid.org/0000-0003-4390-685X"},"institutions":[{"id":"https://openalex.org/I2802423016","display_name":"WinnMed","ror":"https://ror.org/02s47w807","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2802423016"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hugo Botha","raw_affiliation_strings":["Mayo Clinic"],"affiliations":[{"raw_affiliation_string":"Mayo Clinic","institution_ids":["https://openalex.org/I2802423016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5010878109"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31537474,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9965999722480774,"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/classifier","display_name":"Classifier (UML)","score":0.771541953086853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7643210887908936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6538058519363403},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5230292081832886},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5040463805198669},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4477533996105194},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4417393207550049},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41471827030181885},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3929552137851715},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3592917323112488}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.771541953086853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7643210887908936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6538058519363403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5230292081832886},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5040463805198669},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4477533996105194},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4417393207550049},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41471827030181885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3929552137851715},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3592917323112488},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389789","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/asru57964.2023.10389789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W180052447","https://openalex.org/W1597628276","https://openalex.org/W1999453191","https://openalex.org/W2018363392","https://openalex.org/W2042750648","https://openalex.org/W2064675550","https://openalex.org/W2073499295","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2509830706","https://openalex.org/W2767111132","https://openalex.org/W2942897167","https://openalex.org/W2943497673","https://openalex.org/W2953273646","https://openalex.org/W3097777922","https://openalex.org/W3101840241","https://openalex.org/W3112347997","https://openalex.org/W3157419554","https://openalex.org/W3158679803","https://openalex.org/W3169064633","https://openalex.org/W3186142473","https://openalex.org/W3205171606","https://openalex.org/W4210787527","https://openalex.org/W4221145109","https://openalex.org/W4221161761","https://openalex.org/W4224885307","https://openalex.org/W4225535697","https://openalex.org/W4226287929","https://openalex.org/W4312172251","https://openalex.org/W4320005044","https://openalex.org/W4323066695","https://openalex.org/W4372260311","https://openalex.org/W4385245566","https://openalex.org/W6635702766","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6755477022","https://openalex.org/W6790830454","https://openalex.org/W6799359866","https://openalex.org/W6810007534","https://openalex.org/W6810673746","https://openalex.org/W6810982695","https://openalex.org/W6850218400"],"related_works":["https://openalex.org/W4288365749","https://openalex.org/W2936497627","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W3098382480","https://openalex.org/W4287598411","https://openalex.org/W3094871513","https://openalex.org/W3100913109","https://openalex.org/W3198458223","https://openalex.org/W3126642501"],"abstract_inverted_index":{"We":[0,16,93],"propose":[1],"a":[2,21,43,51,100,154],"Perceiver-based":[3],"sequence":[4],"classifier":[5,19],"to":[6,56,75,168,195],"detect":[7,189],"abnormalities":[8,191],"in":[9],"speech":[10,141,190],"reflective":[11],"of":[12,33,46,60,67,79,122,156],"several":[13],"neurological":[14],"disorders.":[15],"combine":[17],"this":[18],"with":[20,137,183],"Universal":[22],"Speech":[23],"Model":[24],"(USM)":[25],"that":[26,71,130],"is":[27,54,70,86,132,145],"trained":[28],"on":[29,99],"12":[30],"million":[31],"hours":[32],"diverse":[34],"audio":[35],"recordings.":[36],"Our":[37,107],"model":[38,76,97,108],"compresses":[39],"long":[40],"sequences":[41],"into":[42],"small":[44],"set":[45],"class-specific":[47],"latent":[48],"representations":[49],"and":[50,85,113,117,134,159,162,182],"factorized":[52],"projection":[53],"used":[55],"predict":[57],"different":[58,77,83],"attributes":[59],"the":[61,80,88,95,104,138,150,171],"disordered":[62],"input":[63,81],"speech.":[64],"The":[65,178],"benefit":[66],"our":[68],"approach":[69],"it":[72],"allows":[73],"us":[74],"regions":[78],"for":[82],"classes":[84],"at":[87],"same":[89],"time":[90],"data":[91],"efficient.":[92],"evaluated":[94],"proposed":[96],"extensively":[98],"curated":[101],"corpus":[102],"from":[103,149],"Mayo":[105],"Clinic.":[106],"outperforms":[109],"standard":[110],"transformer":[111],"(80.9%)":[112],"perceiver":[114],"(81.8%)":[115],"models":[116],"achieves":[118],"an":[119],"average":[120],"accuracy":[121],"83.1%.":[123],"With":[124],"limited":[125],"task-specific":[126],"data,":[127],"we":[128],"find":[129],"pretraining":[131,136],"important":[133],"surprisingly":[135],"un-related":[139],"automatic":[140],"recognition":[142],"(ASR)":[143],"task":[144],"also":[146],"beneficial.":[147],"Encodings":[148],"middle":[151],"layers":[152],"provide":[153],"mix":[155],"both":[157],"acoustic":[158],"phonetic":[160],"information":[161],"achieve":[163],"best":[164],"prediction":[165],"results":[166,179],"compared":[167],"just":[169],"using":[170],"final":[172],"layer":[173],"encodings":[174],"(83.1%":[175],"vs":[176],"79.6%).":[177],"are":[180],"promising":[181],"further":[184],"refinements":[185],"may":[186],"help":[187],"clinicians":[188],"without":[192],"needing":[193],"access":[194],"highly":[196],"specialized":[197],"speech-language":[198],"pathologists.":[199]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}