{"id":"https://openalex.org/W3160577380","doi":"https://doi.org/10.1109/icassp39728.2021.9413982","title":"Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning","display_name":"Investigating Local and Global Information for Automated Audio Captioning with Transfer Learning","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160577380","doi":"https://doi.org/10.1109/icassp39728.2021.9413982","mag":"3160577380"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/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":true,"raw_author_name":"Xuenan Xu","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"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":"Heinrich Dinkel","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, 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":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":false,"raw_author_name":"Zeyu Xie","raw_affiliation_strings":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, 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":["Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence SpeechLab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025827045"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.2661,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95125085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"909"},"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":0.9952999949455261,"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":0.9912999868392944,"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":0.8223704099655151},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7678476572036743},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5475704073905945},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5471873879432678},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.529433012008667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.459440141916275},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4330655038356781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4120948016643524},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35605889558792114}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8223704099655151},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7678476572036743},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5475704073905945},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5471873879432678},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.529433012008667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.459440141916275},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4330655038356781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120948016643524},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35605889558792114},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5099999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1902237438","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2695712842","https://openalex.org/W2916103538","https://openalex.org/W2945761034","https://openalex.org/W2964121744","https://openalex.org/W2964213897","https://openalex.org/W2964308564","https://openalex.org/W3015591594","https://openalex.org/W3016059657","https://openalex.org/W3042165234","https://openalex.org/W3094550259","https://openalex.org/W3097791920","https://openalex.org/W6631190155","https://openalex.org/W6678262379","https://openalex.org/W6679434410","https://openalex.org/W6682631176","https://openalex.org/W6898505805"],"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/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Automated":[0],"audio":[1,10,18,57,67,73],"captioning":[2],"(AAC)":[3],"aims":[4],"at":[5],"generating":[6],"summarizing":[7],"descriptions":[8],"for":[9,38,66],"clips.":[11],"Multitudinous":[12],"concepts":[13,53],"are":[14,76,95,114,148],"described":[15],"in":[16,55,129],"an":[17],"caption,":[19],"ranging":[20],"from":[21],"local":[22,88,100,142],"information":[23,30,143,155],"such":[24],"as":[25],"sound":[26],"events":[27],"to":[28,48,86,97,125,151],"global":[29,90,102,154],"like":[31],"acoustic":[32],"scenery.":[33],"Currently,":[34],"the":[35,41,46,56,71,117],"mainstream":[36],"paradigm":[37],"AAC":[39,118,152],"is":[40,139],"end-to-end":[42],"encoder-decoder":[43],"architecture,":[44],"expecting":[45],"encoder":[47],"learn":[49],"all":[50,130],"levels":[51],"of":[52],"embedded":[54],"automatically.":[58],"This":[59],"paper":[60],"first":[61],"proposes":[62],"a":[63,82,126],"topic":[64,134],"model":[65],"descriptions,":[68],"comprehensively":[69],"analyzing":[70],"hierarchical":[72],"topics":[74],"that":[75,141],"commonly":[77],"covered.":[78],"We":[79],"then":[80],"explore":[81],"transfer":[83,135],"learning":[84,147],"scheme":[85],"access":[87],"and":[89,101,108,122,144,156],"information.":[91],"Two":[92],"source":[93],"tasks":[94],"identified":[96],"respectively":[98],"represent":[99],"information,":[103],"being":[104],"Audio":[105],"Tagging":[106],"(AT)":[107],"Acoustic":[109],"Scene":[110],"Classification":[111],"(ASC).":[112],"Experiments":[113],"conducted":[115],"on":[116],"benchmark":[119],"dataset":[120],"Clotho":[121],"Audiocaps,":[123],"amounting":[124],"vast":[127],"increase":[128],"eight":[131],"metrics":[132],"with":[133],"learning.":[136,159],"Further,":[137],"it":[138],"discovered":[140],"abstract":[145],"representation":[146],"more":[149],"crucial":[150],"than":[153],"temporal":[157],"relationship":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
