{"id":"https://openalex.org/W4408354739","doi":"https://doi.org/10.1109/icassp49660.2025.10889886","title":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","display_name":"Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354739","doi":"https://doi.org/10.1109/icassp49660.2025.10889886"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039455173","display_name":"Gongyu Chen","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":true,"raw_author_name":"Gongyu Chen","raw_affiliation_strings":["College of Computer and Science, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"College of Computer and Science, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035330165","display_name":"Haomin Zhang","orcid":"https://orcid.org/0000-0002-9439-1625"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haomin Zhang","raw_affiliation_strings":["AI Lab, Giant Network"],"affiliations":[{"raw_affiliation_string":"AI Lab, Giant Network","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111268242","display_name":"Chaofan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaofan Ding","raw_affiliation_strings":["AI Lab, Giant Network"],"affiliations":[{"raw_affiliation_string":"AI Lab, Giant Network","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103053228","display_name":"Zihao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Chen","raw_affiliation_strings":["AI Lab, Giant Network"],"affiliations":[{"raw_affiliation_string":"AI Lab, Giant Network","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021368755","display_name":"Xinhan Di","orcid":"https://orcid.org/0009-0001-8855-8628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhan Di","raw_affiliation_strings":["AI Lab, Giant Network"],"affiliations":[{"raw_affiliation_string":"AI Lab, Giant Network","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039455173"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02070238,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9797000288963318,"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":0.9797000288963318,"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/T11309","display_name":"Music and Audio Processing","score":0.9488000273704529,"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/T10860","display_name":"Speech and Audio Processing","score":0.9469000101089478,"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/computer-science","display_name":"Computer science","score":0.7788448333740234},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6545318961143494},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5078607201576233},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48734936118125916},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.48394206166267395},{"id":"https://openalex.org/keywords/audio-equipment","display_name":"Audio equipment","score":0.4194795787334442},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3471464514732361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3349243998527527},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1197899878025055},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06848800182342529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788448333740234},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6545318961143494},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5078607201576233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48734936118125916},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.48394206166267395},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.4194795787334442},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3471464514732361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3349243998527527},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1197899878025055},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06848800182342529},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889886","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2936774411","https://openalex.org/W3081192838","https://openalex.org/W3198377975","https://openalex.org/W4225299287","https://openalex.org/W4226442948","https://openalex.org/W4312310776","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385823125","https://openalex.org/W4390872773","https://openalex.org/W4392903801","https://openalex.org/W4392909369","https://openalex.org/W4392909554","https://openalex.org/W4402112119","https://openalex.org/W4402915838","https://openalex.org/W6638699884","https://openalex.org/W6736723571","https://openalex.org/W6747331233","https://openalex.org/W6757817989","https://openalex.org/W6780178746","https://openalex.org/W6788125050","https://openalex.org/W6791353385","https://openalex.org/W6803227292","https://openalex.org/W6803864336","https://openalex.org/W6804111167","https://openalex.org/W6809947431","https://openalex.org/W6842574522","https://openalex.org/W6842760672","https://openalex.org/W6852818750","https://openalex.org/W6853249747","https://openalex.org/W6853774274"],"related_works":["https://openalex.org/W2997567050","https://openalex.org/W1483272040","https://openalex.org/W4283377908","https://openalex.org/W1526712007","https://openalex.org/W1533421371","https://openalex.org/W1603736412","https://openalex.org/W2003050223","https://openalex.org/W2091777911","https://openalex.org/W2766405861","https://openalex.org/W2360975119"],"abstract_inverted_index":{"One":[0],"fascinating":[1],"aspect":[2],"of":[3,66,75,81,88],"pre-trained":[4],"Audio-Language":[5],"Models":[6],"(ALMs)":[7],"learning":[8,60,95,108],"is":[9,77,100],"their":[10],"impressive":[11],"zero-shot":[12,37,140],"generalization":[13],"capability":[14],"and":[15,72,93],"test-time":[16,113],"adaptation":[17,31,114,132],"(TTA)":[18,32],"methods":[19,33],"aiming":[20],"to":[21,40,49,135],"improve":[22],"domain":[23,73],"performance":[24,141],"without":[25,61,116],"annotations.":[26],"However,":[27],"previous":[28],"test":[29,91,98],"time":[30],"for":[34,110],"ALMs":[35,76],"in":[36,43,143],"classification":[38],"tend":[39],"be":[41],"stuck":[42],"incorrect":[44],"model":[45],"predictions.":[46],"In":[47],"order":[48],"further":[50],"boost":[51],"the":[52,111,146],"performance,":[53],"we":[54,103],"propose":[55,104],"multiple":[56,85],"guidance":[57,65,80],"on":[58,68,124],"prompt":[59],"annotated":[62,117],"labels.":[63,118],"First,":[64],"consistency":[67,83],"both":[69,82],"context":[70],"tokens":[71,74],"set.":[78,101],"Second,":[79],"across":[84,96,128],"augmented":[86],"views":[87],"each":[89],"single":[90],"sample":[92],"contrastive":[94],"different":[97],"samples":[99],"Third,":[102],"a":[105],"corresponding":[106],"end-end":[107],"framework":[109],"proposed":[112,131],"method":[115,133],"We":[119],"extensively":[120],"evaluate":[121],"our":[122,130],"approach":[123],"12":[125],"downstream":[126],"tasks":[127],"domains,":[129],"leads":[134],"4.41%":[136],"(max":[137],"7.50%)":[138],"average":[139],"improvement":[142],"comparison":[144],"with":[145],"state-of-the-art":[147],"models.":[148]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}