{"id":"https://openalex.org/W4315701203","doi":"https://doi.org/10.1109/icassp49357.2023.10097021","title":"Spice+: Evaluation of Automatic Audio Captioning Systems with Pre-Trained Language Models","display_name":"Spice+: Evaluation of Automatic Audio Captioning Systems with Pre-Trained Language Models","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4315701203","doi":"https://doi.org/10.1109/icassp49357.2023.10097021"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10097021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5009358735","display_name":"F\u00e9lix Gontier","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"F\u00e9lix Gontier","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria,Loria,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria,Loria,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria,Loria,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria,Loria,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015868219","display_name":"Christophe Cerisara","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Cerisara","raw_affiliation_strings":["Université de Lorraine, CNRS, Inria,Loria,France,F-54000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Inria,Loria,France,F-54000","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9943000078201294,"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":0.887622594833374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8216187357902527},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6586732864379883},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6377295255661011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6290013790130615},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6054744720458984},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5987203121185303},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.5861851572990417},{"id":"https://openalex.org/keywords/spice","display_name":"Spice","score":0.5723239183425903},{"id":"https://openalex.org/keywords/fluency","display_name":"Fluency","score":0.5050645470619202},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.47853001952171326},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43895310163497925},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4289616346359253},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41739973425865173},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4113547205924988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3551428020000458},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1529461145401001},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09909817576408386}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.887622594833374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216187357902527},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6586732864379883},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6377295255661011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290013790130615},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6054744720458984},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5987203121185303},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.5861851572990417},{"id":"https://openalex.org/C2780077345","wikidata":"https://www.wikidata.org/wiki/Q16891888","display_name":"Spice","level":2,"score":0.5723239183425903},{"id":"https://openalex.org/C2777413886","wikidata":"https://www.wikidata.org/wiki/Q3276013","display_name":"Fluency","level":2,"score":0.5050645470619202},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.47853001952171326},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43895310163497925},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4289616346359253},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41739973425865173},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4113547205924988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3551428020000458},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1529461145401001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09909817576408386},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10097021","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10097021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5611049820","display_name":"Learning to understand audio scenes","funder_award_id":"ANR-18-CE23-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1956340063","https://openalex.org/W2066134726","https://openalex.org/W2097606805","https://openalex.org/W2108325777","https://openalex.org/W2128856065","https://openalex.org/W2133459682","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2740840489","https://openalex.org/W2949376505","https://openalex.org/W2964213897","https://openalex.org/W2970529259","https://openalex.org/W2970641574","https://openalex.org/W3015591594","https://openalex.org/W3016473712","https://openalex.org/W3018647120","https://openalex.org/W3103022576","https://openalex.org/W3205860970","https://openalex.org/W6725318829","https://openalex.org/W6742695268","https://openalex.org/W6775935039","https://openalex.org/W6776148200","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2905433371","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/W2330246314"],"abstract_inverted_index":{"Audio":[0],"captioning":[1,16,91,158],"aims":[2],"at":[3],"describing":[4],"acoustic":[5],"scenes":[6],"with":[7,32,51,62,102,115],"natural":[8],"language.":[9],"Systems":[10],"are":[11],"currently":[12],"evaluated":[13],"by":[14],"image":[15],"metrics":[17,31],"CIDEr":[18],"and":[19,49,68,81,120,149],"SPICE.":[20],"However,":[21],"recent":[22],"studies":[23],"have":[24],"highlighted":[25],"a":[26,41,63,69,87],"poor":[27],"correlation":[28],"of":[29,43,72,79,147,157],"these":[30],"human":[33],"assessments.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"propose":[39],"SPICE+,":[40],"modification":[42],"SPICE":[44],"that":[45,93,127],"improves":[46],"caption":[47],"annotation":[48,66],"comparison":[50],"pre-trained":[52],"language":[53],"models.":[54],"The":[55],"metric":[56,107,129],"parses":[57],"captions":[58],"to":[59,97,132],"semantic":[60,83,142],"graphs":[61],"deep":[64],"dependency":[65],"model":[67],"refined":[70],"set":[71],"linguistic":[73],"rules,":[74],"then":[75],"compares":[76],"sentence":[77,135],"embeddings":[78],"candidate":[80],"reference":[82],"elements.":[84],"We":[85],"formulate":[86],"score":[88],"for":[89],"general-purpose":[90],"evaluation,":[92],"can":[94,150],"be":[95],"tailored":[96],"more":[98],"specific":[99],"applications.":[100],"Combined":[101],"fluency":[103],"error":[104],"detection,":[105],"the":[106,112,128,133,139,155],"achieves":[108],"competitive":[109],"performance":[110],"on":[111,118,122,154],"FENSE":[113],"benchmark,":[114],"84.0%":[116],"accuracy":[117],"AudioCaps":[119],"74.1%":[121],"Clotho.":[123],"Further":[124],"experiments":[125],"show":[126],"behaves":[130],"similarly":[131],"full":[134],"embedding":[136],"similarity,":[137],"while":[138],"decomposition":[140],"into":[141],"elements":[143],"allows":[144],"better":[145],"interpretability":[146],"scores":[148],"provide":[151],"additional":[152],"information":[153],"properties":[156],"systems.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}