{"id":"https://openalex.org/W4404037229","doi":"https://doi.org/10.1109/mlsp58920.2024.10734763","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","display_name":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","publication_year":2024,"publication_date":"2024-09-22","ids":{"openalex":"https://openalex.org/W4404037229","doi":"https://doi.org/10.1109/mlsp58920.2024.10734763"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp58920.2024.10734763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp58920.2024.10734763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5101889011","display_name":"Yi Yuan","orcid":"https://orcid.org/0000-0002-7121-0983"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yi Yuan","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108961732","display_name":"Zhuo Chen","orcid":"https://orcid.org/0009-0007-3882-3810"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Chen","raw_affiliation_strings":["ByteDance,China"],"affiliations":[{"raw_affiliation_string":"ByteDance,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407730","display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025827045","display_name":"Xuenan Xu","orcid":"https://orcid.org/0000-0001-8718-1278"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060687079","display_name":"Dongya Jia","orcid":"https://orcid.org/0000-0002-6307-8580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongya Jia","raw_affiliation_strings":["ByteDance,China"],"affiliations":[{"raw_affiliation_string":"ByteDance,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055175414","display_name":"Yuanzhe Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanzhe Chen","raw_affiliation_strings":["ByteDance,China"],"affiliations":[{"raw_affiliation_string":"ByteDance,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Surrey,United Kingdom","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101889011"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":3.9149,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94611191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9886999726295471,"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":0.9886999726295471,"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":0.9758999943733215,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.951200008392334,"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/computer-science","display_name":"Computer science","score":0.7124625444412231},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45667123794555664},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37654566764831543},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.35768190026283264},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05808621644973755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124625444412231},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45667123794555664},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37654566764831543},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35768190026283264},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05808621644973755}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp58920.2024.10734763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp58920.2024.10734763","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11208910610002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G7697158467","display_name":"AI for Sound","funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2965373594","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3152698349","https://openalex.org/W3176445421","https://openalex.org/W3198377975","https://openalex.org/W3198452188","https://openalex.org/W3215466129","https://openalex.org/W4221157007","https://openalex.org/W4226442948","https://openalex.org/W4284898017","https://openalex.org/W4307106676","https://openalex.org/W4308163867","https://openalex.org/W4312310776","https://openalex.org/W4312825288","https://openalex.org/W4372260310","https://openalex.org/W4372260330","https://openalex.org/W4372260340","https://openalex.org/W4372266552","https://openalex.org/W4385822467","https://openalex.org/W4385822843","https://openalex.org/W4386076015","https://openalex.org/W4387969422","https://openalex.org/W4390873321","https://openalex.org/W4392909615","https://openalex.org/W4403780823","https://openalex.org/W6766673545","https://openalex.org/W6791353385","https://openalex.org/W6803567076","https://openalex.org/W6804092457","https://openalex.org/W6810940779","https://openalex.org/W6846655393","https://openalex.org/W6849109464","https://openalex.org/W6849549116"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Contrastive":[0],"language-audio":[1],"pretraining":[2],"(CLAP)":[3],"has":[4],"been":[5],"developed":[6],"to":[7,27,67,86],"align":[8],"the":[9,88,112],"representations":[10],"of":[11,115],"audio":[12,32,43,72],"and":[13,20,33,45,64,100,118,128],"language,":[14],"achieving":[15],"remarkable":[16],"performance":[17],"in":[18,102,110],"retrieval":[19,44],"classification":[21],"tasks.":[22,105],"However,":[23],"current":[24],"CLAP":[25,56,89],"struggles":[26],"capture":[28],"temporal":[29,113],"information":[30],"within":[31],"text":[34],"features,":[35],"presenting":[36],"substantial":[37],"limitations":[38],"for":[39,71],"tasks":[40],"such":[41],"as":[42],"generation.":[46],"To":[47],"address":[48],"this":[49],"gap,":[50],"we":[51],"introduce":[52],"T-CLAP,":[53],"a":[54,79,123],"temporal-enhanced":[55],"model.":[57],"We":[58,96],"use":[59],"Large":[60],"Language":[61],"Models":[62],"(LLMs)":[63],"mixed-up":[65],"strategies":[66],"generate":[68],"temporal-contrastive":[69],"captions":[70],"clips":[73],"from":[74],"extensive":[75],"audio-text":[76],"datasets.":[77],"Subsequently,":[78],"new":[80],"temporal-focused":[81],"contrastive":[82],"loss":[83],"is":[84],"designed":[85],"fine-tune":[87],"model":[90],"by":[91,122],"incorporating":[92],"these":[93],"synthetic":[94],"data.":[95],"conduct":[97],"comprehensive":[98],"experiments":[99],"analysis":[101],"multiple":[103],"downstream":[104],"T-CLAP":[106],"shows":[107],"improved":[108],"capability":[109],"capturing":[111],"relationship":[114],"sound":[116],"events":[117],"outperforms":[119],"state-of-the-art":[120],"models":[121,129],"significant":[124],"margin.":[125],"Our":[126],"code":[127],"will":[130],"be":[131],"released":[132],"soon.":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}