{"id":"https://openalex.org/W4403635980","doi":"https://doi.org/10.1109/tpami.2024.3484658","title":"Prompt Tuning of Deep Neural Networks for Speaker-Adaptive Visual Speech Recognition","display_name":"Prompt Tuning of Deep Neural Networks for Speaker-Adaptive Visual Speech Recognition","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4403635980","doi":"https://doi.org/10.1109/tpami.2024.3484658","pmid":"https://pubmed.ncbi.nlm.nih.gov/39437301"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3484658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3484658","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0002-6514-0018"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-6514-0018","affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038009350","display_name":"Hyung-Il Kim","orcid":"https://orcid.org/0000-0001-6425-549X"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyung-Il Kim","raw_affiliation_strings":["Visual Intelligence Research Section, Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","Visual Intelligence Research Section, Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6425-549X","affiliations":[{"raw_affiliation_string":"Visual Intelligence Research Section, Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Visual Intelligence Research Section, Artificial Intelligence Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038798134","display_name":"Yong Man Ro","orcid":"https://orcid.org/0000-0001-5306-6853"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong Man Ro","raw_affiliation_strings":["Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5306-6853","affiliations":[{"raw_affiliation_string":"Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Image and Video Systems Lab., School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0501,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.9506451,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"47","issue":"2","first_page":"1042","last_page":"1055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9412999749183655,"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/speech-recognition","display_name":"Speech recognition","score":0.7787702679634094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7237837314605713},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6619294881820679},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5674036741256714},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.49966883659362793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49711278080940247},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4382491111755371},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40899235010147095}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7787702679634094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7237837314605713},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6619294881820679},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5674036741256714},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.49966883659362793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49711278080940247},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4382491111755371},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40899235010147095}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D049250","descriptor_name":"Speech Recognition Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3484658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3484658","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:39437301","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39437301","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":107,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W567546468","https://openalex.org/W1513862252","https://openalex.org/W1735317348","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2015143272","https://openalex.org/W2033256038","https://openalex.org/W2033310064","https://openalex.org/W2048526313","https://openalex.org/W2051328185","https://openalex.org/W2064675550","https://openalex.org/W2074417845","https://openalex.org/W2081258893","https://openalex.org/W2094147890","https://openalex.org/W2098805611","https://openalex.org/W2108598243","https://openalex.org/W2108759471","https://openalex.org/W2112021726","https://openalex.org/W2113814270","https://openalex.org/W2117553576","https://openalex.org/W2122272452","https://openalex.org/W2124629003","https://openalex.org/W2127141656","https://openalex.org/W2150769028","https://openalex.org/W2153149612","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2160884118","https://openalex.org/W2162042984","https://openalex.org/W2163973301","https://openalex.org/W2194775991","https://openalex.org/W2398406965","https://openalex.org/W2403731734","https://openalex.org/W2551572271","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2796339975","https://openalex.org/W2803974577","https://openalex.org/W2890952074","https://openalex.org/W2963166524","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2969985801","https://openalex.org/W2971387592","https://openalex.org/W2972473456","https://openalex.org/W2996970093","https://openalex.org/W3006713268","https://openalex.org/W3015830103","https://openalex.org/W3016008406","https://openalex.org/W3016011581","https://openalex.org/W3044438666","https://openalex.org/W3091641623","https://openalex.org/W3097777922","https://openalex.org/W3098267758","https://openalex.org/W3127645834","https://openalex.org/W3162293946","https://openalex.org/W3162707322","https://openalex.org/W3167917117","https://openalex.org/W3185341429","https://openalex.org/W3195455417","https://openalex.org/W3197567540","https://openalex.org/W3198377975","https://openalex.org/W3203789665","https://openalex.org/W3205193540","https://openalex.org/W3210278576","https://openalex.org/W4205991051","https://openalex.org/W4213328902","https://openalex.org/W4224319127","https://openalex.org/W4285247752","https://openalex.org/W4287020098","https://openalex.org/W4297841411","https://openalex.org/W4307286264","https://openalex.org/W4307965990","https://openalex.org/W4312310776","https://openalex.org/W4312638101","https://openalex.org/W4312651322","https://openalex.org/W4312975593","https://openalex.org/W4313055276","https://openalex.org/W4385245566","https://openalex.org/W4386076680","https://openalex.org/W4391021666","https://openalex.org/W4392903956","https://openalex.org/W4404792841","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6639480849","https://openalex.org/W6640212811","https://openalex.org/W6640425456","https://openalex.org/W6679436768","https://openalex.org/W6682864246","https://openalex.org/W6732872814","https://openalex.org/W6752946794","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6763296340","https://openalex.org/W6778883912","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6802744804","https://openalex.org/W6803359641","https://openalex.org/W6810168380","https://openalex.org/W6810676379","https://openalex.org/W6838865580","https://openalex.org/W6839526036","https://openalex.org/W6845709062"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W2640905660"],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"(VSR)":[3],"aims":[4],"to":[5,21,30,49,55,115,138],"infer":[6],"speech":[7],"into":[8],"text":[9],"depending":[10],"on":[11,18,64,93,166,230],"lip":[12,32],"movements":[13],"alone.":[14],"As":[15],"it":[16],"focuses":[17],"visual":[19],"information":[20],"model":[22,63,104,141,165,190],"the":[23,39,57,61,102,108,125,127,130,139,152,159,162,188,201,213,219,225],"speech,":[24],"its":[25],"performance":[26,44,58,160,202],"is":[27,143,191,216,228],"inherently":[28],"sensitive":[29],"personal":[31],"appearances":[33],"and":[34,36,129,147,203,233,238],"movements,":[35],"this":[37,53],"makes":[38],"VSR":[40,62,140,164,235],"models":[41],"show":[42,157],"degraded":[43],"when":[45,212],"they":[46],"are":[47],"applied":[48,137],"unseen":[50,65,167],"speakers.":[51],"In":[52],"paper,":[54],"remedy":[56],"degradation":[59],"of":[60,72,96,100,123,145,161,178,205,208,224],"speakers,":[66],"we":[67,90,119,156,210],"propose":[68],"prompt":[69,110,154,214],"tuning":[70,111,215],"methods":[71,112],"Deep":[73],"Neural":[74],"Networks":[75],"(DNNs)":[76],"for":[77],"speaker-adaptive":[78],"VSR.":[79],"Specifically,":[80],"motivated":[81],"by":[82,173,199],"recent":[83],"advances":[84],"in":[85,149],"Natural":[86],"Language":[87],"Processing":[88],"(NLP),":[89],"finetune":[91],"prompts":[92,133],"adaptation":[94,179],"data":[95,180],"target":[97],"speakers":[98,168],"instead":[99],"modifying":[101],"pre-trained":[103,163,189],"parameters.":[105],"Different":[106],"from":[107],"previous":[109],"mainly":[113],"limited":[114],"Transformer":[116,148],"variant":[117],"architecture,":[118],"explore":[120],"different":[121,206],"types":[122,207],"prompts,":[124,209],"addition,":[126],"padding,":[128],"concatenation":[131],"form":[132],"that":[134,158],"can":[135,169],"be":[136,170],"which":[142],"composed":[144],"CNN":[146],"general.":[150],"With":[151],"proposed":[153,226],"tuning,":[155],"largely":[171],"improved":[172],"using":[174],"a":[175],"small":[176],"amount":[177],"(e.g.,":[181],"less":[182],"than":[183],"5":[184],"minutes),":[185],"even":[186],"if":[187],"already":[192],"developed":[193],"with":[194],"large":[195],"speaker":[196],"variations.":[197],"Moreover,":[198],"analyzing":[200],"parameters":[204],"investigate":[211],"preferred":[217],"over":[218],"finetuning":[220],"methods.":[221],"The":[222],"effectiveness":[223],"method":[227],"evaluated":[229],"both":[231],"word-":[232],"sentence-level":[234],"databases,":[236],"LRW-ID":[237],"GRID.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
