{"id":"https://openalex.org/W4403791285","doi":"https://doi.org/10.1145/3664647.3681347","title":"Boosting Speech Recognition Robustness to Modality-Distortion with Contrast-Augmented Prompts","display_name":"Boosting Speech Recognition Robustness to Modality-Distortion with Contrast-Augmented Prompts","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791285","doi":"https://doi.org/10.1145/3664647.3681347"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681347","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101485171","display_name":"Dongjie Fu","orcid":"https://orcid.org/0009-0000-7682-7678"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongjie Fu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-7682-7678","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9708-3225","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103359200","display_name":"Xiaoda Yang","orcid":"https://orcid.org/0009-0002-7297-4536"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoda Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-7297-4536","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114416483","display_name":"Wang Hanting","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Hanting","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-4032-9257","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6121-0384","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011966","display_name":"Tao Jin","orcid":"https://orcid.org/0000-0003-3564-1628"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Jin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3564-1628","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":1.1943,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83079278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3838","last_page":"3847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7647883892059326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145017981529236},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7026826739311218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6969109773635864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5194965600967407},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4631006419658661},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.41779080033302307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35469868779182434}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7647883892059326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145017981529236},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7026826739311218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6969109773635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194965600967407},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4631006419658661},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.41779080033302307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35469868779182434},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3681347","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1530404542","https://openalex.org/W1897240248","https://openalex.org/W2963785710","https://openalex.org/W3006974783","https://openalex.org/W3162293946","https://openalex.org/W3162596541","https://openalex.org/W3198377975","https://openalex.org/W3205717164","https://openalex.org/W4205991051","https://openalex.org/W4281479158","https://openalex.org/W4297841719","https://openalex.org/W4304083163","https://openalex.org/W4312238419","https://openalex.org/W4385823147","https://openalex.org/W4386071467","https://openalex.org/W4386071547","https://openalex.org/W4386075647","https://openalex.org/W4386075949","https://openalex.org/W4387968213","https://openalex.org/W4390872424","https://openalex.org/W4390873467","https://openalex.org/W4390873695","https://openalex.org/W4392567168","https://openalex.org/W4392895351","https://openalex.org/W4393148276","https://openalex.org/W4402670354","https://openalex.org/W4402716427","https://openalex.org/W4403791608","https://openalex.org/W4403792076"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W1538046993","https://openalex.org/W2571255492","https://openalex.org/W4239293476"],"abstract_inverted_index":{"In":[0,65,103],"the":[1,15,25,68,89,96,112,121,136,154,165,178,210],"burgeoning":[2],"field":[3],"of":[4,51,67,114,117,212],"Audio-Visual":[5],"Speech":[6],"Recognition":[7],"(AVSR),":[8],"extant":[9],"research":[10],"has":[11],"predominantly":[12],"concentrated":[13],"on":[14,196],"training":[16],"paradigms":[17],"tailored":[18],"for":[19,81,205],"high-quality":[20],"resources.":[21,214],"However,":[22],"owing":[23],"to":[24,87,95,105,131,138,143,176],"challenges":[26],"inherent":[27],"in":[28,62,119],"real-world":[29],"data":[30,33],"collection,":[31],"audio-visual":[32,41,167,206],"are":[34],"frequently":[35],"affected":[36],"by":[37,99],"modality-distortion,":[38,134],"which":[39],"encompasses":[40],"asynchrony,":[42],"video":[43],"noise":[44],"and":[45,123,190],"audio":[46,122],"noise.":[47],"The":[48],"recognition":[49,141,208],"accuracy":[50],"existing":[52],"AVSR":[53],"method":[54],"is":[55,216],"significantly":[56],"compromised":[57],"when":[58],"multiple":[59,159],"modality-distortion":[60,82],"coexist":[61],"low-resource":[63],"data.":[64],"light":[66],"above":[69],"challenges,":[70],"we":[71,108,127,157,170],"propose":[72],"PCD:":[73],"cluster-Prompt":[74],"with":[75,147],"Contrastive":[76],"Decomposition,":[77],"a":[78,172],"robust":[79],"framework":[80],"speech":[83,140,207],"recognition,":[84],"specifically":[85],"devised":[86],"transpose":[88],"pre-trained":[90,166],"knowledge":[91,189],"from":[92],"high-resource":[93],"domain":[94,98],"targeted":[97],"leveraging":[100],"contrast-augmented":[101],"prompts.":[102],"contrast":[104],"previous":[106],"studies,":[107],"take":[109],"into":[110],"consideration":[111],"possibility":[113],"various":[115,144,182],"types":[116],"distortion":[118,145],"both":[120],"visual":[124],"modalities.":[125],"Concretely,":[126],"design":[128,171],"bespoke":[129],"prompts":[130],"delineate":[132],"each":[133],"guiding":[135],"model":[137],"achieve":[139],"applicable":[142],"scenarios":[146],"quite":[148],"few":[149],"learnable":[150],"parameters.":[151],"To":[152],"materialize":[153],"prompt":[155],"mechanism,":[156],"employ":[158],"cluster-based":[160],"strategies":[161],"that":[162,200],"better":[163],"suits":[164],"model.":[168],"Additionally,":[169],"contrastive":[173],"decomposition":[174],"mechanism":[175],"restrict":[177],"explicit":[179],"relationships":[180],"among":[181],"modality":[183,192],"conditions,":[184],"given":[185],"their":[186],"shared":[187],"task":[188],"disparate":[191],"priors.":[193],"Extensive":[194],"results":[195],"LRS2":[197],"dataset":[198],"demonstrate":[199],"PCD":[201],"achieves":[202],"state-of-the-art":[203],"performance":[204],"under":[209],"constraints":[211],"distorted":[213],"Code":[215],"available":[217],"at":[218],"https://github.com/ballooncatt/PCD.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}