{"id":"https://openalex.org/W4224933373","doi":"https://doi.org/10.1109/icassp43922.2022.9746786","title":"Audio-Text Retrieval in Context","display_name":"Audio-Text Retrieval in Context","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224933373","doi":"https://doi.org/10.1109/icassp43922.2022.9746786"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746786","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5012206466","display_name":"Siyu Lou","orcid":"https://orcid.org/0000-0002-8046-0052"},"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":true,"raw_author_name":"Siyu Lou","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081865665","display_name":"Mengyue Wu","orcid":"https://orcid.org/0000-0002-5599-8707"},"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":"Mengyue Wu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"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":"Kai Yu","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012206466"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.9149,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.93327038,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4793","last_page":"4797"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9973000288009644,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9868999719619751,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8506688475608826},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5785934925079346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5543557405471802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4841092824935913},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.48315733671188354},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4827134311199188},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4766857624053955},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47550827264785767},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.45717814564704895},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41312727332115173},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37787869572639465},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3546995520591736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506688475608826},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5785934925079346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5543557405471802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4841092824935913},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.48315733671188354},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4827134311199188},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4766857624053955},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47550827264785767},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.45717814564704895},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41312727332115173},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37787869572639465},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3546995520591736},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746786","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1905882502","https://openalex.org/W2010486494","https://openalex.org/W2012592962","https://openalex.org/W2064675550","https://openalex.org/W2112912048","https://openalex.org/W2194775991","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2706729717","https://openalex.org/W2796207103","https://openalex.org/W2940092410","https://openalex.org/W2951019013","https://openalex.org/W2965458216","https://openalex.org/W3015371781","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3198452188","https://openalex.org/W6636510571","https://openalex.org/W6676647902","https://openalex.org/W6739520758","https://openalex.org/W6750041603","https://openalex.org/W6766582784"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"Audio-text":[0],"retrieval":[1,74],"based":[2],"on":[3,82,100,125,129],"natural":[4],"language":[5],"descriptions":[6],"is":[7,51],"a":[8,43,65,83,119],"challenging":[9],"task.":[10],"It":[11],"involves":[12],"learning":[13],"cross-modality":[14],"alignments":[15],"between":[16],"long":[17],"sequences":[18],"under":[19],"inadequate":[20],"data":[21],"conditions.":[22],"In":[23],"this":[24],"work,":[25],"we":[26,46,69,77],"investigate":[27],"several":[28],"audio":[29,62],"features":[30,63,80],"as":[31,33],"well":[32],"sequence":[34],"aggregation":[35,67],"methods":[36],"for":[37],"better":[38],"audio-text":[39,73,127],"alignment.":[40],"Moreover,":[41],"through":[42],"qualitative":[44],"analysis":[45],"observe":[47],"that":[48],"semantic":[49],"mapping":[50],"more":[52],"important":[53],"than":[54],"temporal":[55],"relations":[56],"in":[57],"contextual":[58,72],"retrieval.":[59],"Using":[60],"pre-trained":[61,81],"and":[64,88,103,106,135],"descriptor-based":[66],"method,":[68],"build":[70],"our":[71,116],"system.":[75,114],"Specifically,":[76],"utilize":[78],"PANNs":[79],"large":[84],"sound":[85],"event":[86],"dataset":[87],"NetRVLAD":[89],"pooling,":[90],"which":[91],"directly":[92],"works":[93],"with":[94,110],"averaged":[95],"descriptors.":[96],"Experiments":[97],"are":[98,108],"conducted":[99],"the":[101,111],"AudioCaps":[102],"CLOTHO":[104],"datasets,":[105],"results":[107],"compared":[109],"previous":[112],"state-of-the-art":[113],"With":[115],"proposed":[117],"system,":[118],"significant":[120],"improvement":[121],"has":[122],"been":[123],"achieved":[124],"bidirectional":[126],"retrieval,":[128],"all":[130],"metrics":[131],"including":[132],"recall,":[133],"median":[134],"mean":[136],"rank.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}
