{"id":"https://openalex.org/W4402980322","doi":"https://doi.org/10.1109/icme57554.2024.10688214","title":"Audiolog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning","display_name":"Audiolog: LLMs-Powered Long Audio Logging with Hybrid Token-Semantic Contrastive Learning","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980322","doi":"https://doi.org/10.1109/icme57554.2024.10688214"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5027263923","display_name":"Jisheng Bai","orcid":"https://orcid.org/0000-0002-9803-8212"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jisheng Bai","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029196482","display_name":"Han Yin","orcid":"https://orcid.org/0009-0008-9413-1859"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Yin","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mou Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Acoustics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Acoustics,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035317975","display_name":"Dongyuan Shi","orcid":"https://orcid.org/0000-0002-8832-6595"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dongyuan Shi","raw_affiliation_strings":["Nanyang Technological University,School of Electrical &#x0026; Electronic Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical &#x0026; Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Nanyang Technological University,School of Electrical &#x0026; Electronic Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical &#x0026; Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065376714","display_name":"Jianfeng Chen","orcid":"https://orcid.org/0000-0002-7281-7138"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Chen","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054558832","display_name":"Susanto Rahardja","orcid":"https://orcid.org/0000-0003-0831-6934"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Susanto Rahardja","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.996999979019165,"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":0.9937000274658203,"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/security-token","display_name":"Security token","score":0.6933808922767639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685853898525238},{"id":"https://openalex.org/keywords/logging","display_name":"Logging","score":0.49601349234580994},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.23481079936027527},{"id":"https://openalex.org/keywords/forestry","display_name":"Forestry","score":0.0838814377784729}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6933808922767639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685853898525238},{"id":"https://openalex.org/C125620115","wikidata":"https://www.wikidata.org/wiki/Q845249","display_name":"Logging","level":2,"score":0.49601349234580994},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.23481079936027527},{"id":"https://openalex.org/C97137747","wikidata":"https://www.wikidata.org/wiki/Q38112","display_name":"Forestry","level":1,"score":0.0838814377784729},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688214","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688214","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2759976799","https://openalex.org/W3015700860","https://openalex.org/W3094550259","https://openalex.org/W3138516171","https://openalex.org/W3178592608","https://openalex.org/W4226377790","https://openalex.org/W4226442948","https://openalex.org/W4280567182","https://openalex.org/W4312120802","https://openalex.org/W4312765536","https://openalex.org/W4315926819","https://openalex.org/W4367556039","https://openalex.org/W4372260310","https://openalex.org/W4400033239","https://openalex.org/W6778883912","https://openalex.org/W6784011672","https://openalex.org/W6791429434","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889"],"abstract_inverted_index":{"Previous":[0],"studies":[1],"in":[2,9,101,112],"automated":[3],"audio":[4,23,34,51,67,129,151],"captioning":[5],"have":[6],"faced":[7],"difficulties":[8],"accurately":[10],"capturing":[11],"the":[12,47,74,80,95,113,118,134,142],"complete":[13],"temporal":[14],"details":[15],"of":[16,73,117,136],"acoustic":[17,59,75,102],"scenes":[18],"and":[19,89,105],"events":[20],"within":[21],"long":[22,128,150],"sequences.":[24,152],"This":[25],"paper":[26],"presents":[27],"AudioLog,":[28],"a":[29],"large":[30],"language":[31],"models":[32],"(LLMs)-powered":[33],"logging":[35],"system":[36,82,97],"with":[37,86],"hybrid":[38,58],"token-semantic":[39,50],"contrastive":[40,55],"learning.":[41],"Specifically,":[42],"we":[43,78],"propose":[44],"to":[45,65,120,145],"fine-tune":[46],"pre-trained":[48],"hierarchical":[49],"Transformer":[52],"by":[53],"incorporating":[54],"learning":[56],"between":[57],"representations.":[60],"We":[61],"then":[62],"leverage":[63,146],"LLMs":[64,121,147],"generate":[66],"logs":[68],"that":[69,94,123],"summarize":[70,127],"textual":[71],"descriptions":[72],"environment.":[76],"Finally,":[77],"evaluate":[79],"AudioLog":[81,124],"on":[83],"two":[84],"datasets":[85],"both":[87],"scene":[88,103],"event":[90,107],"annotations.":[91],"Experiments":[92],"show":[93],"proposed":[96],"achieves":[98],"exceptional":[99],"performance":[100],"classification":[104],"sound":[106],"detection,":[108],"surpassing":[109],"existing":[110],"methods":[111],"field.":[114],"Further":[115],"analysis":[116],"prompts":[119],"demonstrates":[122],"can":[125],"effectively":[126],"sequences<sup":[130],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[131],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[132],"To":[133],"best":[135],"our":[137],"knowledge,":[138],"this":[139],"approach":[140],"is":[141],"first":[143],"attempt":[144],"for":[148],"summarizing":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
