{"id":"https://openalex.org/W4392909622","doi":"https://doi.org/10.1109/icassp48485.2024.10446582","title":"C-CLAPA: Improving Text-Audio Cross Domain Retrieval with Captioning and Augmentations","display_name":"C-CLAPA: Improving Text-Audio Cross Domain Retrieval with Captioning and Augmentations","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909622","doi":"https://doi.org/10.1109/icassp48485.2024.10446582"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446582","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5014191634","display_name":"Amit Sofer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160816","display_name":"Alzheimer's Association of Israel","ror":"https://ror.org/0561tpp86","country_code":"IL","type":"nonprofit","lineage":["https://openalex.org/I4210160816"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Amit Sofer","raw_affiliation_strings":["OriginAI,Ramat-Gan,Israel","OriginAI, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OriginAI,Ramat-Gan,Israel","institution_ids":["https://openalex.org/I4210160816"]},{"raw_affiliation_string":"OriginAI, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I4210160816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080213609","display_name":"Shlomo E. Chazan","orcid":"https://orcid.org/0000-0002-6614-6112"},"institutions":[{"id":"https://openalex.org/I4210160816","display_name":"Alzheimer's Association of Israel","ror":"https://ror.org/0561tpp86","country_code":"IL","type":"nonprofit","lineage":["https://openalex.org/I4210160816"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shlomo E. Chazan","raw_affiliation_strings":["OriginAI,Ramat-Gan,Israel","OriginAI, Ramat-Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OriginAI,Ramat-Gan,Israel","institution_ids":["https://openalex.org/I4210160816"]},{"raw_affiliation_string":"OriginAI, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I4210160816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210160816"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03404212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"8040","last_page":"8044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.9926999807357788,"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":0.9746999740600586,"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/closed-captioning","display_name":"Closed captioning","score":0.9549285173416138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8155530691146851},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5846262574195862},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5117964148521423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5035547614097595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4340892434120178},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.337989866733551},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09970030188560486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.058736652135849}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9549285173416138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155530691146851},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5846262574195862},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5117964148521423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5035547614097595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4340892434120178},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.337989866733551},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09970030188560486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.058736652135849},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446582","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W2765407302","https://openalex.org/W2936774411","https://openalex.org/W2945761034","https://openalex.org/W2965373594","https://openalex.org/W3015591594","https://openalex.org/W3138516171","https://openalex.org/W3184735396","https://openalex.org/W3198452188","https://openalex.org/W4210913346","https://openalex.org/W4221147537","https://openalex.org/W4221157007","https://openalex.org/W4226442948","https://openalex.org/W4229042118","https://openalex.org/W4288089799","https://openalex.org/W4322718191","https://openalex.org/W4372260310","https://openalex.org/W4372266552","https://openalex.org/W4385822467","https://openalex.org/W6745136726","https://openalex.org/W6766673545","https://openalex.org/W6769627184","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6838439425","https://openalex.org/W6846849257","https://openalex.org/W6849549116","https://openalex.org/W6850625674"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"In":[0,56,129,141],"this":[1,130],"paper,":[2],"we":[3,132,145],"introduce":[4],"Captioning":[5],"decoder":[6,61,78],"Contrastive":[7],"Language-Audio":[8],"Pretraining":[9],"with":[10,53,138],"data":[11,187],"Augmantation":[12],"(C-CLAPA),":[13],"a":[14,54,59,67,125],"new":[15],"Audio-Text":[16],"model":[17,120,135,151],"for":[18,34,40],"the":[19,35,38,41,47,70,74,84,114,134,154,163,172,175,182,185],"Cross":[20],"Domain":[21],"Retrieval":[22],"(CDR)":[23],"task.":[24],"The":[25,43,118,158],"model\u2019s":[26],"backbone":[27],"is":[28,62,79,91,121],"comprised":[29],"of":[30,73,184],"two":[31],"encoders,":[32],"one":[33],"text":[36,88,103],"and":[37,90,102],"other":[39],"audio.":[42],"embedding":[44,71,86],"vectors":[45],"from":[46,69],"different":[48],"modalities":[49],"are":[50,110],"commonly":[51],"trained":[52,123],"contrastive-loss.":[55],"our":[57,142,150],"approach,":[58,131],"captioning":[60],"also":[63],"used":[64,80,92,111],"to":[65,81,112],"generate":[66],"text-description":[68],"vector":[72],"audio":[75,85],"sample.":[76],"This":[77],"ensure":[82],"that":[83,149],"encapsulates":[87],"information,":[89],"only":[93],"on":[94,136,162],"training":[95,116,127],"stage.":[96],"Data":[97],"preparations":[98],"including":[99],"filtering,":[100],"augmentations":[101],"generation":[104],"utilizing":[105],"Large":[106],"Language":[107],"Models":[108],"(LLMs),":[109],"extend":[113],"current":[115,155],"dataset.":[117],"proposed":[119,176],"finally":[122],"using":[124],"curriculum":[126],"procedure.":[128],"train":[133],"datasets":[137],"increasing":[139],"quality.":[140],"empirical":[143,169],"investigation,":[144],"provide":[146],"compelling":[147],"evidence":[148,170],"significantly":[152],"surpasses":[153],"State":[156],"Of":[157],"Art":[159],"(SOTA)":[160],"models":[161],"available":[164],"benchmarks.":[165],"Ablation":[166],"analysis":[167],"provides":[168],"showcasing":[171],"advantages":[173],"in":[174],"architectural":[177],"design":[178],"as":[179,181],"well":[180],"efficacy":[183],"employed":[186],"processing":[188],"methodology.":[189]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}