{"id":"https://openalex.org/W3205860970","doi":"https://doi.org/10.1109/icassp43922.2022.9746427","title":"Can Audio Captions Be Evaluated With Image Caption Metrics?","display_name":"Can Audio Captions Be Evaluated With Image Caption Metrics?","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205860970","doi":"https://doi.org/10.1109/icassp43922.2022.9746427","mag":"3205860970"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746427","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/A5089075841","display_name":"Zelin Zhou","orcid":null},"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":"Zelin Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018465248","display_name":"Zhiling Zhang","orcid":"https://orcid.org/0000-0001-7807-2264"},"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":"Zhiling Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, 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,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, 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":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, 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,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101906756","display_name":"Kenny Q. Zhu","orcid":"https://orcid.org/0000-0003-3782-3230"},"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":"Kenny Q. Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5089075841"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.3729,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.8715401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"981","last_page":"985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980999827384949,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9922999739646912,"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/closed-captioning","display_name":"Closed captioning","score":0.8855583667755127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.839000940322876},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7008960247039795},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6161031723022461},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6122258901596069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5557265281677246},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5499864220619202},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5202204585075378},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4131658971309662},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.41101711988449097},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.332050621509552}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8855583667755127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839000940322876},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7008960247039795},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6161031723022461},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6122258901596069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5557265281677246},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5499864220619202},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5202204585075378},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4131658971309662},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.41101711988449097},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.332050621509552},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746427","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746427","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W1975879668","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2788277448","https://openalex.org/W2896457183","https://openalex.org/W2896780650","https://openalex.org/W2916103538","https://openalex.org/W2936695845","https://openalex.org/W2945761034","https://openalex.org/W2950446064","https://openalex.org/W2963341956","https://openalex.org/W2963672599","https://openalex.org/W2964213897","https://openalex.org/W2970641574","https://openalex.org/W2970858040","https://openalex.org/W2996403597","https://openalex.org/W3015591594","https://openalex.org/W3035252911","https://openalex.org/W3094550259","https://openalex.org/W3160577380","https://openalex.org/W3204363391","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6725318829","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W4388002133","https://openalex.org/W2894446834"],"abstract_inverted_index":{"Automated":[0],"audio":[1,10,18],"captioning":[2,25],"aims":[3],"at":[4],"generating":[5],"textual":[6],"descriptions":[7],"for":[8,130],"an":[9],"clip.":[11],"To":[12,101],"evaluate":[13],"the":[14,42,54,114,133],"quality":[15],"of":[16,44,56,80,116],"generated":[17],"captions,":[19],"previous":[20],"works":[21],"directly":[22],"adopt":[23],"image":[24],"metrics":[26,89,140],"like":[27],"SPICE":[28],"and":[29,71,121],"CIDEr,":[30],"without":[31],"justifying":[32],"their":[33,103],"suitability":[34],"in":[35,92,118],"this":[36],"new":[37],"domain,":[38],"which":[39],"may":[40],"mislead":[41],"development":[43],"advanced":[45],"models.":[46],"This":[47],"problem":[48],"is":[49],"still":[50],"unstudied":[51],"due":[52],"to":[53,83,126],"lack":[55],"human":[57,96],"judgment":[58],"datasets":[59],"on":[60,98],"caption":[61],"quality.":[62],"Therefore,":[63],"we":[64,105,112],"first":[65],"construct":[66],"two":[67],"evaluation":[68],"benchmarks,":[69,136],"AudioCaps-Eval":[70],"Clotho-Eval.":[72],"They":[73],"are":[74,90],"established":[75,135],"with":[76,95],"pairwise":[77],"comparison":[78],"instead":[79],"absolute":[81],"rating":[82],"achieve":[84],"better":[85],"inter-annotator":[86],"agreement.":[87],"Current":[88],"found":[91],"poor":[93],"correlation":[94],"annotations":[97],"these":[99],"datasets.":[100],"overcome":[102],"limitations,":[104],"propose":[106],"a":[107,122],"metric":[108],"named":[109],"FENSE,":[110],"where":[111],"combine":[113],"strength":[115],"Sentence-BERT":[117],"capturing":[119],"similarity,":[120],"novel":[123],"Error":[124],"Detector":[125],"penalize":[127],"erroneous":[128],"sentences":[129],"robustness.":[131],"On":[132],"newly":[134],"FENSE":[137],"outperforms":[138],"current":[139],"by":[141],"14-25%":[142],"accuracy.":[143],"<sup":[144],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[146]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
