{"id":"https://openalex.org/W4392903479","doi":"https://doi.org/10.1109/icassp48485.2024.10448154","title":"Parameter Efficient Audio Captioning with Faithful Guidance Using Audio-Text Shared Latent Representation","display_name":"Parameter Efficient Audio Captioning with Faithful Guidance Using Audio-Text Shared Latent Representation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903479","doi":"https://doi.org/10.1109/icassp48485.2024.10448154"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5050134369","display_name":"Arvind Krishna Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Arvind Krishna Sridhar","raw_affiliation_strings":["Qualcomm Technologies"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053583465","display_name":"Yinyi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yinyi Guo","raw_affiliation_strings":["Qualcomm Technologies"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009801065","display_name":"Erik Visser","orcid":null},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Erik Visser","raw_affiliation_strings":["Qualcomm Technologies"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies","institution_ids":["https://openalex.org/I19268510"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037744622","display_name":"Rehana Mahfuz","orcid":"https://orcid.org/0000-0002-9974-1137"},"institutions":[{"id":"https://openalex.org/I19268510","display_name":"Qualcomm (United Kingdom)","ror":"https://ror.org/04d3djg48","country_code":"GB","type":"company","lineage":["https://openalex.org/I19268510","https://openalex.org/I4210087596"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rehana Mahfuz","raw_affiliation_strings":["Qualcomm Technologies"],"affiliations":[{"raw_affiliation_string":"Qualcomm Technologies","institution_ids":["https://openalex.org/I19268510"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5050134369"],"corresponding_institution_ids":["https://openalex.org/I19268510"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65160358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1181","last_page":"1185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9940000176429749,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9904000163078308,"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":0.8200726509094238},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8015190958976746},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5419171452522278},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5415748357772827},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.496650755405426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4490821063518524},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41098207235336304},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10299938917160034},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09005871415138245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200726509094238},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8015190958976746},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5419171452522278},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5415748357772827},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.496650755405426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490821063518524},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41098207235336304},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10299938917160034},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09005871415138245},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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/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/icassp48485.2024.10448154","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":23,"referenced_works":["https://openalex.org/W2945761034","https://openalex.org/W2962735233","https://openalex.org/W2970641574","https://openalex.org/W3007007518","https://openalex.org/W3015591594","https://openalex.org/W3115021520","https://openalex.org/W3189036352","https://openalex.org/W3196974791","https://openalex.org/W4309674289","https://openalex.org/W4310882533","https://openalex.org/W4322747194","https://openalex.org/W4372260310","https://openalex.org/W4380353763","https://openalex.org/W4384918448","https://openalex.org/W4385573912","https://openalex.org/W4385574044","https://openalex.org/W4386566667","https://openalex.org/W4400033239","https://openalex.org/W6799494382","https://openalex.org/W6802577842","https://openalex.org/W6847342293","https://openalex.org/W6852874933","https://openalex.org/W6854866820"],"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":{"There":[0],"has":[1],"been":[2],"significant":[3],"research":[4],"on":[5,32,67,162],"developing":[6],"pretrained":[7],"transformer":[8],"architectures":[9],"for":[10,43,57,75],"multimodal-to-text":[11],"generation":[12],"tasks.":[13],"Albeit":[14],"performance":[15,96,184],"improvements,":[16],"such":[17],"models":[18,94,100],"frequently":[19],"suffer":[20],"from":[21],"hallucination":[22],"and":[23,62,152,165,176,185],"large":[24],"memory":[25],"footprint":[26],"making":[27],"them":[28],"challenging":[29],"to":[30,98,119],"deploy":[31],"edge":[33],"devices.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,51,79],"address":[39],"both":[40],"these":[41],"issues":[42],"the":[44,106,110,122,134,139,157,167],"application":[45],"of":[46,146,159],"automated":[47],"audio":[48,60,92,153,174],"captioning.":[49],"First,":[50],"propose":[52,80],"a":[53,81],"data":[54],"augmentation":[55],"technique":[56],"generating":[58],"hallucinated":[59],"captions":[61],"show":[63,156],"that":[64,89],"similarity":[65,141,178],"based":[66],"an":[68,114],"audio-text":[69,115],"shared":[70,116],"latent":[71,117,143],"space":[72],"is":[73,131],"suitable":[74],"detecting":[76],"hallucination.":[77],"Then,":[78],"parameter":[82],"efficient":[83],"inference":[84],"time":[85],"faithful":[86],"decoding":[87,108],"algorithm":[88,161],"enables":[90],"smaller":[91,111],"captioning":[93,175],"with":[95,102,125],"equivalent":[97],"larger":[99],"trained":[101],"more":[103],"data.":[104],"During":[105],"beam":[107,135],"step,":[109],"model":[112],"utilizes":[113],"representation":[118,144],"semantically":[120],"align":[121],"generated":[123],"text":[124],"corresponding":[126],"input":[127],"audio.":[128],"Faithful":[129],"guidance":[130],"introduced":[132],"into":[133],"probability":[136],"by":[137],"incorporating":[138],"cosine":[140],"between":[142,183],"projections":[145],"greedy":[147],"rolled":[148],"out":[149],"intermediate":[150],"beams":[151],"clip.":[154],"We":[155],"efficacy":[158],"our":[160],"benchmark":[163],"datasets":[164],"evaluate":[166],"proposed":[168],"scheme":[169],"against":[170],"baselines":[171],"using":[172],"conventional":[173],"semantic":[177],"metrics":[179],"while":[180],"illustrating":[181],"tradeoffs":[182],"complexity.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}