{"id":"https://openalex.org/W4224926581","doi":"https://doi.org/10.1109/icassp43922.2022.9746834","title":"Diversity-Controllable and Accurate Audio Captioning Based on Neural Condition","display_name":"Diversity-Controllable and Accurate Audio Captioning Based on Neural Condition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224926581","doi":"https://doi.org/10.1109/icassp43922.2022.9746834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746834","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/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":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence 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 X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence 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 X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence X-LANCE Lab,Department of Computer Science and Engineering AI Institute,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering AI Institute, MoE Key Lab of Artificial Intelligence X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025827045"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.6074,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63644948,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"971","last_page":"975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9962999820709229,"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":0.9506279230117798},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8520798683166504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115710020065308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4960521161556244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47269347310066223},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45249128341674805},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44430339336395264},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.43897074460983276},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4192643165588379},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36548346281051636},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09357482194900513}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9506279230117798},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8520798683166504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115710020065308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4960521161556244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47269347310066223},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45249128341674805},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44430339336395264},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.43897074460983276},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4192643165588379},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36548346281051636},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09357482194900513},{"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/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746834","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746834","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":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7099999785423279}],"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":27,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2133512280","https://openalex.org/W2133564696","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2604178507","https://openalex.org/W2788277448","https://openalex.org/W2790137376","https://openalex.org/W2901988662","https://openalex.org/W2916103538","https://openalex.org/W2962968835","https://openalex.org/W2963173418","https://openalex.org/W2963206148","https://openalex.org/W2963456134","https://openalex.org/W2963594498","https://openalex.org/W2982669287","https://openalex.org/W3015591594","https://openalex.org/W3094550259","https://openalex.org/W3097791920","https://openalex.org/W3112467147","https://openalex.org/W3122335742","https://openalex.org/W3160577380","https://openalex.org/W6679434410","https://openalex.org/W6725318829","https://openalex.org/W6744104549","https://openalex.org/W6749107692","https://openalex.org/W6787564935"],"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/W2330246314","https://openalex.org/W3009270862"],"abstract_inverted_index":{"With":[0],"the":[1,41,46,60,69,78,81,99,106,109,113,121,124,140,150,168,172],"incorporation":[2],"of":[3,83],"pre-training,":[4],"transfer":[5],"learning":[6],"and":[7,35,101,139,155],"keyword":[8],"input,":[9],"notable":[10],"improvement":[11],"has":[12],"been":[13],"made":[14],"in":[15,24,45,51,144],"audio":[16,21],"captioning":[17,29,95,125,137],"on":[18,153],"generating":[19],"accurate":[20],"event":[22],"descriptions":[23],"recent":[25],"years.":[26],"However,":[27,73],"current":[28],"models":[30],"tend":[31],"to":[32,58,64,97,129],"generate":[33,130],"repetitive":[34],"generic":[36],"sentences":[37],"which":[38],"often":[39,76],"contain":[40],"most":[42],"frequent":[43],"patterns":[44],"training":[47],"data.":[48],"Some":[49],"works":[50],"natural":[52],"language":[53],"generation":[54],"make":[55],"an":[56,145],"effort":[57],"improve":[59,167],"diversity":[61,79,100,170],"by":[62,116],"attending":[63],"specific":[65],"contents":[66],"or":[67],"increasing":[68],"generated":[70],"caption":[71],"number.":[72],"these":[74],"approaches":[75],"enhance":[77],"with":[80,105,132,162,171],"sacrifice":[82],"description":[84],"accuracy.":[85],"In":[86],"this":[87],"work,":[88],"we":[89],"propose":[90],"a":[91,117,133],"novel":[92],"neural":[93,110,118],"conditional":[94],"model":[96,126,138],"balance":[98],"accuracy":[102,174],"trade-off.":[103],"Compared":[104],"statistical":[107],"condition,":[108,123],"condition":[111],"is":[112,127],"posterior":[114],"given":[115],"discriminator.":[119],"Given":[120],"reference":[122],"trained":[128,143],"captions":[131],"similar":[134],"posterior.":[135],"The":[136,157],"discriminator":[141],"are":[142],"adversarial":[146],"way.":[147],"We":[148],"evaluate":[149],"proposed":[151],"approach":[152,165],"Clotho":[154],"Audiocaps.":[156],"results":[158],"show":[159],"that":[160],"compared":[161],"baselines,":[163],"our":[164],"can":[166],"output":[169],"least":[173],"decline.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
