{"id":"https://openalex.org/W4408355359","doi":"https://doi.org/10.1109/icassp49660.2025.10889071","title":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","display_name":"SLAM-AAC: Enhancing Audio Captioning with Paraphrasing Augmentation and CLAP-Refine through LLMs","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355359","doi":"https://doi.org/10.1109/icassp49660.2025.10889071"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5090739497","display_name":"Wenxi Chen","orcid":"https://orcid.org/0000-0002-7938-9033"},"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":"Wenxi Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100438492","display_name":"Ziyang Ma","orcid":"https://orcid.org/0000-0002-0623-9114"},"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":"Ziyang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104326367","display_name":"Xiquan Li","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":false,"raw_author_name":"Xiquan Li","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,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,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114117046","display_name":"Yuzhe Liang","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":false,"raw_author_name":"Yuzhe Liang","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068357345","display_name":"Zhisheng Zheng","orcid":"https://orcid.org/0000-0001-7761-9790"},"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":"Zhisheng Zheng","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101293966","display_name":"Xie Chen","orcid":"https://orcid.org/0009-0004-4458-0753"},"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":"Xie Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence, X-LANCE Lab,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5090739497"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":56.4997,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99799487,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9577000141143799,"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":0.9352999925613403,"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":0.9428554773330688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432568430900574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47818854451179504},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47787871956825256},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33666130900382996}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9428554773330688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432568430900574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47818854451179504},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47787871956825256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33666130900382996},{"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:10.1109/icassp49660.2025.10889071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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":37,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1494198834","https://openalex.org/W1956340063","https://openalex.org/W2081580037","https://openalex.org/W2399550240","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2936774411","https://openalex.org/W2949376505","https://openalex.org/W2963216553","https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W3094550259","https://openalex.org/W3162331882","https://openalex.org/W3198694222","https://openalex.org/W3205860970","https://openalex.org/W4226442948","https://openalex.org/W4307323391","https://openalex.org/W4372260310","https://openalex.org/W4387609319","https://openalex.org/W4392902647","https://openalex.org/W4392902953","https://openalex.org/W4392904001","https://openalex.org/W4400033239","https://openalex.org/W4401023891","https://openalex.org/W4402112418","https://openalex.org/W6678262379","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6780379688","https://openalex.org/W6796581206","https://openalex.org/W6847076894","https://openalex.org/W6847363464","https://openalex.org/W6848208918","https://openalex.org/W6854866820","https://openalex.org/W6861626678"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Automated":[0],"Audio":[1],"Captioning":[2],"(AAC)":[3],"aims":[4],"to":[5,45,63,103,140,147],"generate":[6],"natural":[7],"textual":[8,31,73,167],"descriptions":[9,168],"for":[10,159],"input":[11,178],"audio":[12,17,28,66,130],"signals.":[13],"Recent":[14],"progress":[15],"in":[16,36,96,152],"pre-trained":[18],"models":[19,23],"and":[20,30,52,120,191],"large":[21],"language":[22],"(LLMs)":[24],"has":[25],"significantly":[26],"enhanced":[27],"understanding":[29],"reasoning":[32],"capabilities,":[33],"making":[34],"improvements":[35],"AAC":[37,48],"possible.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,99,134,163],"propose":[43],"SLAM-AAC":[44,184],"further":[46],"enhance":[47],"with":[49,72],"paraphrasing":[50,101],"augmentation":[51,102],"CLAP-Refine":[53,138],"through":[54],"LLMs.":[55],"Our":[56],"approach":[57],"uses":[58],"the":[59,87,93,105,114,136,148,156,166,177],"self-supervised":[60],"EAT":[61],"model":[62,158],"extract":[64],"fine-grained":[65],"representations,":[67],"which":[68],"are":[69],"then":[70],"aligned":[71],"embeddings":[74],"via":[75],"lightweight":[76],"linear":[77],"layers.":[78],"The":[79],"caption":[80],"generation":[81],"LLM":[82],"is":[83],"efficiently":[84],"fine-tuned":[85],"using":[86],"LoRA":[88],"adapter.":[89],"Drawing":[90],"inspiration":[91],"from":[92,125],"back-translation":[94],"method":[95],"machine":[97],"translation,":[98],"implement":[100],"expand":[104],"Clotho":[106,189],"dataset":[107],"during":[108],"pre-training.":[109],"This":[110],"strategy":[111,139,151],"helps":[112],"alleviate":[113],"limitation":[115],"of":[116,129],"scarce":[117],"audio-text":[118,160],"pairs":[119],"generates":[121],"more":[122],"diverse":[123],"captions":[124],"a":[126],"small":[127],"set":[128],"clips.":[131],"During":[132],"inference,":[133],"introduce":[135],"plug-and-play":[137],"fully":[141],"exploit":[142],"multiple":[143,171],"decoding":[144],"outputs,":[145],"akin":[146],"n-best":[149],"rescoring":[150],"speech":[153],"recognition.":[154],"Using":[155],"CLAP":[157],"similarity":[161],"calculation,":[162],"could":[164],"select":[165],"generated":[169],"by":[170],"searching":[172],"beams":[173],"that":[174,183],"best":[175],"match":[176],"audio.":[179],"Experimental":[180],"results":[181],"show":[182],"achieves":[185],"state-of-the-art":[186],"performance":[187],"on":[188],"V2":[190],"AudioCaps,":[192],"surpassing":[193],"previous":[194],"mainstream":[195],"models.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}