{"id":"https://openalex.org/W4406461881","doi":"https://doi.org/10.1109/slt61566.2024.10832263","title":"Optimizing Dysarthria Wake-Up Word Spotting: an End-to-End Approach For SLT 2024 LRDWWS Challenge","display_name":"Optimizing Dysarthria Wake-Up Word Spotting: an End-to-End Approach For SLT 2024 LRDWWS Challenge","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461881","doi":"https://doi.org/10.1109/slt61566.2024.10832263"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832263","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/A5047396754","display_name":"Shuiyun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuiyun Liu","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087994947","display_name":"Yuxiang Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiang Kong","raw_affiliation_strings":["Xiaomi Inc.,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114198820","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0008-7069-979X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113987256","display_name":"Weiji Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiji Zhuang","raw_affiliation_strings":["Xiaomi Inc.,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073011099","display_name":"Peng Gao","orcid":"https://orcid.org/0009-0006-6593-2150"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Gao","raw_affiliation_strings":["Xiaomi Inc.,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362605","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-8353-0423"},"institutions":[{"id":"https://openalex.org/I862669128","display_name":"Xiaomi (China)","ror":"https://ror.org/029f7bn57","country_code":"CN","type":"company","lineage":["https://openalex.org/I862669128"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc.,China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc.,China","institution_ids":["https://openalex.org/I862669128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047396754"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.3474,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6665661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"578","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9990000128746033,"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":0.9929999709129333,"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/spotting","display_name":"Spotting","score":0.8870939016342163},{"id":"https://openalex.org/keywords/dysarthria","display_name":"Dysarthria","score":0.7166171073913574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6595814228057861},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6420840620994568},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5822741389274597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5721849799156189},{"id":"https://openalex.org/keywords/wake","display_name":"Wake","score":0.42328691482543945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33346763253211975},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16806542873382568},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.15519222617149353},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1367897093296051},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1129203736782074}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8870939016342163},{"id":"https://openalex.org/C2777639682","wikidata":"https://www.wikidata.org/wiki/Q225957","display_name":"Dysarthria","level":2,"score":0.7166171073913574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6595814228057861},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6420840620994568},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5822741389274597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5721849799156189},{"id":"https://openalex.org/C48939323","wikidata":"https://www.wikidata.org/wiki/Q294879","display_name":"Wake","level":2,"score":0.42328691482543945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33346763253211975},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16806542873382568},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.15519222617149353},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1367897093296051},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1129203736782074},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832263","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":[{"display_name":"Climate action","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2398169716","https://openalex.org/W2933138175","https://openalex.org/W2953740025","https://openalex.org/W2963242190","https://openalex.org/W2963628261","https://openalex.org/W2964525587","https://openalex.org/W2972838300","https://openalex.org/W2999996462","https://openalex.org/W3012505451","https://openalex.org/W3016238098","https://openalex.org/W3097777922","https://openalex.org/W3158596343","https://openalex.org/W3161018648","https://openalex.org/W3174329270","https://openalex.org/W3197712601","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W4224932111","https://openalex.org/W4283067311","https://openalex.org/W4297841875","https://openalex.org/W4372263660","https://openalex.org/W4372267500","https://openalex.org/W4375869136","https://openalex.org/W4375869422","https://openalex.org/W4385245566","https://openalex.org/W4385822594","https://openalex.org/W4385823400","https://openalex.org/W4392903308","https://openalex.org/W4402112001","https://openalex.org/W6688816777","https://openalex.org/W6754473786","https://openalex.org/W6780218876","https://openalex.org/W6785297517","https://openalex.org/W6796464841","https://openalex.org/W6801281349","https://openalex.org/W6810037887","https://openalex.org/W6856192284","https://openalex.org/W6857134333"],"related_works":["https://openalex.org/W2757285599","https://openalex.org/W2331173358","https://openalex.org/W2376025146","https://openalex.org/W2969484279","https://openalex.org/W3160456149","https://openalex.org/W2034439647","https://openalex.org/W2168872498","https://openalex.org/W4400873482","https://openalex.org/W3184921334","https://openalex.org/W2028814537"],"abstract_inverted_index":{"Speech":[0],"has":[1],"emerged":[2],"as":[3],"a":[4,101,107,145],"widely":[5],"embraced":[6],"user":[7],"interface":[8],"across":[9],"diverse":[10],"applications.":[11],"However,":[12],"for":[13,39],"individuals":[14],"with":[15,144],"dysarthria,":[16],"the":[17,40,79,114,121,151,159],"inherent":[18],"variability":[19],"in":[20,158],"their":[21],"speech":[22,91],"poses":[23],"significant":[24],"challenges.":[25],"This":[26],"paper":[27],"presents":[28],"an":[29,68,135,140],"end-to-end":[30],"Pretrain-based":[31],"Dual-filter":[32],"Dysarthria":[33,44],"Wake-up":[34],"word":[35,96],"Spotting":[36,47],"(PD-DWS)":[37],"system":[38,51,133],"SLT":[41],"2024":[42],"Low-Resource":[43],"Wake-Up":[45],"Word":[46],"Challenge.":[48],"Specifically,":[49],"our":[50,131],"improves":[52],"performance":[53],"from":[54],"two":[55],"key":[56],"perspectives:":[57],"audio":[58,64],"modeling":[59],"and":[60,94,139],"dual-filter":[61,108],"strategy.":[62],"For":[63],"modeling,":[65],"we":[66],"propose":[67],"innovative":[69],"2":[70,73,75,83],"branch-":[71],"d":[72],"v":[74],"model":[76,89],"based":[77],"on":[78,150],"pre-trained":[80],"data2vec":[81],"$2(\\mathrm{~d}":[82],"\\mathrm{v}":[84],"2)$,":[85],"which":[86],"can":[87],"simultaneously":[88],"automatic":[90],"recognition":[92],"(ASR)":[93],"wake-up":[95],"spotting":[97],"(WWS)":[98],"tasks":[99],"through":[100],"unified":[102],"multi-task":[103],"finetuning":[104],"paradigm.":[105],"Additionally,":[106],"strategy":[109],"is":[110],"introduced":[111],"to":[112],"reduce":[113],"false":[115,123],"accept":[116],"rate":[117,125],"(FAR)":[118],"while":[119],"maintaining":[120],"same":[122],"reject":[124],"(FRR).":[126],"Experimental":[127],"results":[128],"demonstrate":[129],"that":[130],"PD-DWS":[132],"achieves":[134],"FAR":[136],"of":[137,142,148],"0.00321":[138],"FRR":[141],"0.005,":[143],"total":[146],"score":[147],"0.00821":[149],"test-B":[152],"eval":[153],"set,":[154],"securing":[155],"first":[156],"place":[157],"challenge.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
