{"id":"https://openalex.org/W4385807506","doi":"https://doi.org/10.21437/interspeech.2023-2191","title":"A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning","display_name":"A New Benchmark of Aphasia Speech Recognition and Detection Based on E-Branchformer and Multi-task Learning","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385807506","doi":"https://doi.org/10.21437/interspeech.2023-2191"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5101730616","display_name":"Jiyang Tang","orcid":"https://orcid.org/0009-0008-3229-7976"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiyang Tang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101779022","display_name":"William Chen","orcid":"https://orcid.org/0000-0002-3251-3084"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Chen","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043710796","display_name":"Brian MacWhinney","orcid":"https://orcid.org/0000-0002-4988-1342"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian MacWhinney","raw_affiliation_strings":["Department of Psychology, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Psychology, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101730616"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.7283,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87571171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1528","last_page":"1532"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6983000040054321,"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":0.6983000040054321,"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/computer-science","display_name":"Computer science","score":0.7727566957473755},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7199513912200928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6514791250228882},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6276269555091858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48044463992118835},{"id":"https://openalex.org/keywords/aphasia","display_name":"Aphasia","score":0.47365841269493103},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4507009983062744},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15930962562561035},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.10042017698287964},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09407490491867065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7727566957473755},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7199513912200928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6514791250228882},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6276269555091858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48044463992118835},{"id":"https://openalex.org/C2779422653","wikidata":"https://www.wikidata.org/wiki/Q2836","display_name":"Aphasia","level":2,"score":0.47365841269493103},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4507009983062744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15930962562561035},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.10042017698287964},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09407490491867065},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2191","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1353381076","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G1912064254","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4006316252","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4801515358","display_name":null,"funder_award_id":"ACCESS","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4968279142","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G509285653","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5173294414","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G7622549653","display_name":null,"funder_award_id":"213829","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8165146668","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8300691027","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8819975937","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320312143","funder_display_name":"National Centre for Supercomputing Applications"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1992119553","https://openalex.org/W1999318234","https://openalex.org/W2015033691","https://openalex.org/W2099239745","https://openalex.org/W2508777706","https://openalex.org/W2514741789","https://openalex.org/W2786835190","https://openalex.org/W2796439139","https://openalex.org/W2799525243","https://openalex.org/W2808640845","https://openalex.org/W2889294685","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2964309797","https://openalex.org/W2972932001","https://openalex.org/W2988476381","https://openalex.org/W2990699120","https://openalex.org/W2995611200","https://openalex.org/W3006736300","https://openalex.org/W3036601975","https://openalex.org/W3049694110","https://openalex.org/W3095387535","https://openalex.org/W3097109903","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3197140813","https://openalex.org/W3197580070","https://openalex.org/W3201447839","https://openalex.org/W3203147359","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4253871295","https://openalex.org/W4283704748","https://openalex.org/W4284973286","https://openalex.org/W4296070201","https://openalex.org/W4319586123","https://openalex.org/W4319862214","https://openalex.org/W4319862255","https://openalex.org/W4372259817","https://openalex.org/W4385822856"],"related_works":["https://openalex.org/W1485630101","https://openalex.org/W2498017833","https://openalex.org/W112744582","https://openalex.org/W2030059621","https://openalex.org/W2081647779","https://openalex.org/W3033750096","https://openalex.org/W2789919619","https://openalex.org/W2081245617","https://openalex.org/W4234487584","https://openalex.org/W2293457016"],"abstract_inverted_index":{"Aphasia":[0,20,67],"is":[1],"a":[2,16,59],"language":[3],"disorder":[4],"that":[5],"affects":[6],"the":[7,32,43,72,85],"speaking":[8],"ability":[9],"of":[10,12,63,74],"millions":[11],"patients.This":[13],"paper":[14],"presents":[15],"new":[17],"benchmark":[18],"for":[19,65],"speech":[21,28,83,119],"recognition":[22,29],"and":[23,58,94,106],"detection":[24,55],"tasks":[25,49],"using":[26],"state-of-the-art":[27],"techniques":[30],"with":[31],"Aphsia-Bank":[33],"dataset.Specifically,":[34],"we":[35,70],"introduce":[36],"two":[37],"multi-task":[38],"learning":[39],"methods":[40],"based":[41],"on":[42],"CTC/Attention":[44],"architecture":[45],"to":[46,80,99,111],"perform":[47],"both":[48],"simultaneously.Our":[50],"system":[51],"achieves":[52],"state-ofthe-art":[53],"speaker-level":[54],"accuracy":[56],"(97.3%),":[57],"relative":[60],"WER":[61],"reduction":[62],"11%":[64],"moderate":[66],"patients.In":[68],"addition,":[69],"demonstrate":[71],"generalizability":[73],"our":[75,91],"approach":[76],"by":[77],"applying":[78],"it":[79],"another":[81],"disordered":[82,118],"database,":[84],"Demen-tiaBank":[86],"Pitt":[87],"corpus.We":[88],"will":[89],"make":[90],"all-in-one":[92],"recipes":[93,108],"pre-trained":[95],"model":[96],"publicly":[97],"available":[98],"facilitate":[100],"reproducibility.Our":[101],"standardized":[102],"data":[103],"preprocessing":[104],"pipeline":[105],"open-source":[107],"enable":[109],"researchers":[110],"compare":[112],"results":[113],"directly,":[114],"promoting":[115],"progress":[116],"in":[117],"processing.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
