{"id":"https://openalex.org/W4385822843","doi":"https://doi.org/10.21437/interspeech.2023-1614","title":"Enhance Temporal Relations in Audio Captioning with Sound Event Detection","display_name":"Enhance Temporal Relations in Audio Captioning with Sound Event Detection","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822843","doi":"https://doi.org/10.21437/interspeech.2023-1614"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1614","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5000223918","display_name":"Zeyu Xie","orcid":"https://orcid.org/0009-0001-9546-3301"},"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":"Zeyu Xie","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, 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":["MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, 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":["MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, 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":["MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence X-LANCE Lab, Department of Computer Science and Engineering AI Institute, 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/A5000223918"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.0823,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88095681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4179","last_page":"4183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9855999946594238,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9848999977111816,"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":0.7417362928390503},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7410396337509155},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7088951468467712},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5837844014167786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4431461691856384},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.43140920996665955},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3972858190536499},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.292096346616745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26150602102279663},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15736788511276245},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12733131647109985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7417362928390503},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7410396337509155},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7088951468467712},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5837844014167786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4431461691856384},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.43140920996665955},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3972858190536499},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.292096346616745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26150602102279663},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15736788511276245},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12733131647109985},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1614","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1614","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2916103538","https://openalex.org/W2964213897","https://openalex.org/W3015591594","https://openalex.org/W3038899388","https://openalex.org/W3042165234","https://openalex.org/W3094550259","https://openalex.org/W3122335742","https://openalex.org/W3124216180","https://openalex.org/W3135656708","https://openalex.org/W3162999565","https://openalex.org/W3185739472","https://openalex.org/W3186781156","https://openalex.org/W3204936728","https://openalex.org/W3206857696","https://openalex.org/W4226174231","https://openalex.org/W4285865022","https://openalex.org/W4287553315","https://openalex.org/W4295190891"],"related_works":["https://openalex.org/W4320016117","https://openalex.org/W4307856881","https://openalex.org/W2901467237","https://openalex.org/W2547835662","https://openalex.org/W3183824823","https://openalex.org/W3008515501","https://openalex.org/W2020966186","https://openalex.org/W1603949574","https://openalex.org/W4379474567","https://openalex.org/W4385822843"],"abstract_inverted_index":{"Automated":[0],"audio":[1,11,25,30,41,49,65],"captioning":[2,31,99],"aims":[3,69],"at":[4],"generating":[5],"natural":[6],"language":[7],"descriptions":[8],"for":[9],"given":[10],"clips,":[12],"not":[13],"only":[14],"detecting":[15],"and":[16,101],"classifying":[17],"sounds,":[18],"but":[19],"also":[20],"summarizing":[21,64],"the":[22,38,90,109,116],"relationships":[23,74],"between":[24,48],"events.Recent":[26],"research":[27],"advances":[28],"in":[29,43,63,75,97,126],"have":[32,51],"introduced":[33],"additional":[34],"guidance":[35],"to":[36,70,93,107],"improve":[37],"accuracy":[39],"of":[40,128],"events":[42,50],"generated":[44],"sentences.However,":[45],"temporal":[46,73,95,104,118,129],"relations":[47,58],"received":[52],"little":[53],"attention":[54],"while":[55],"revealing":[56],"complex":[57],"is":[59,124],"a":[60,83,98,103],"key":[61],"component":[62],"content.Therefore,":[66],"this":[67],"paper":[68],"better":[71],"capture":[72],"caption":[76],"generation":[77,131],"with":[78],"sound":[79],"event":[80],"detection":[81],"(SED),":[82],"task":[84],"that":[85,121],"locates":[86],"events'":[87],"timestamps.We":[88],"investigate":[89],"best":[91],"approach":[92],"integrate":[94],"information":[96],"model":[100],"propose":[102],"tag":[105],"system":[106],"transform":[108],"timestamps":[110],"into":[111],"comprehensible":[112],"relations.Results":[113],"evaluated":[114],"by":[115],"proposed":[117],"metrics":[119],"suggest":[120],"great":[122],"improvement":[123],"achieved":[125],"terms":[127],"relation":[130],"1":[132],".":[133]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-09T13:55:54.758798","created_date":"2023-08-15T00:00:00"}