{"id":"https://openalex.org/W4392902647","doi":"https://doi.org/10.1109/icassp48485.2024.10446343","title":"Extending Large Language Models for Speech and Audio Captioning","display_name":"Extending Large Language Models for Speech and Audio Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902647","doi":"https://doi.org/10.1109/icassp48485.2024.10446343"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446343","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/A5039664887","display_name":"Changli Tang","orcid":"https://orcid.org/0000-0002-6550-1901"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changli Tang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109693003","display_name":"Wenyi Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyi Yu","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007755497","display_name":"Guangzhi Sun","orcid":"https://orcid.org/0000-0003-3190-497X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhi Sun","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109692700","display_name":"Xianzhao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xianzhao Chen","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101667381","display_name":"Tian Tan","orcid":"https://orcid.org/0000-0002-4723-0044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Tan","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100318193","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-4486-8341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100366031","display_name":"Lu Lu","orcid":"https://orcid.org/0000-0002-6077-0977"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu Lu","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101108160","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["ByteDance"],"affiliations":[{"raw_affiliation_string":"ByteDance","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460206","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7730-5131"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering","Department of Electronic Engineering, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5039664887"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":2.8916,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.917488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11236","last_page":"11240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8462668657302856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8108370900154114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7391349077224731},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7089408040046692},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5692290663719177},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.4231888949871063},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41433802247047424},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41267716884613037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32351744174957275},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31884050369262695},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.29119300842285156},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16152498126029968},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08039826154708862}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8462668657302856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108370900154114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7391349077224731},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7089408040046692},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5692290663719177},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.4231888949871063},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41433802247047424},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41267716884613037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32351744174957275},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31884050369262695},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.29119300842285156},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16152498126029968},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08039826154708862},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446343","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446343","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2949376505","https://openalex.org/W3015591594","https://openalex.org/W3103022576","https://openalex.org/W3198694222","https://openalex.org/W4224932123","https://openalex.org/W4307322847","https://openalex.org/W4322718191","https://openalex.org/W4361866031","https://openalex.org/W4375958083","https://openalex.org/W4376312115","https://openalex.org/W4377130946","https://openalex.org/W4378711593","https://openalex.org/W4380994269","https://openalex.org/W4381827575","https://openalex.org/W4384648427","https://openalex.org/W4389519587","https://openalex.org/W4389524500","https://openalex.org/W4391021666","https://openalex.org/W4392903956","https://openalex.org/W4392909390","https://openalex.org/W4393178509","https://openalex.org/W4400033239","https://openalex.org/W6796581206","https://openalex.org/W6810334672","https://openalex.org/W6846004400","https://openalex.org/W6847363464","https://openalex.org/W6848208918","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851513886","https://openalex.org/W6851847159","https://openalex.org/W6852326057","https://openalex.org/W6852447913","https://openalex.org/W6853094705","https://openalex.org/W6853116092","https://openalex.org/W6853249747","https://openalex.org/W6853998256","https://openalex.org/W6854596735","https://openalex.org/W6855952517"],"related_works":["https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2759241869","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4214489098","https://openalex.org/W46679383"],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(LLMs)":[4],"have":[5],"shown":[6],"promising":[7,130],"visual":[8],"perception":[9,48],"abilities":[10],"by":[11,69,101],"connecting":[12,70],"with":[13,41,73,96,157],"image":[14],"encoders,":[15],"but":[16],"their":[17],"performance":[18],"on":[19,117,138],"auditory":[20,47,74,78,172],"tasks":[21],"has":[22],"not":[23],"yet":[24],"been":[25],"widely":[26,119],"investigated.":[27],"Meanwhile,":[28],"automatic":[29,34],"speech":[30,88,150,159],"recognition":[31],"(ASR)":[32],"and":[33,67,89,112,125,128,141,151,160],"audio":[35,94,152,162],"captioning":[36],"(AAC)":[37],"are":[38,114,136],"often":[39],"achieved":[40,137],"separate":[42],"systems,":[43],"resulting":[44],"in":[45,52,55],"incomplete":[46],"abilities.":[49],"To":[50],"fill":[51],"these":[53],"gaps,":[54],"this":[56],"paper,":[57],"we":[58],"present":[59],"the":[60,84,90,106,118],"first":[61],"study":[62],"that":[63],"achieves":[64],"both":[65],"ASR":[66,111],"AAC":[68,113],"an":[71],"LLM":[72],"encoders.":[75],"A":[76],"dual":[77],"encoder":[79,86,92],"structure":[80],"is":[81,145,165],"proposed,":[82],"integrating":[83],"Whisper":[85],"for":[87,93,110],"BEATs":[91],"events":[95,153],"a":[97,103,166],"high":[98],"temporal":[99],"resolution":[100],"using":[102],"Q-Former":[104],"at":[105],"window":[107],"level.":[108],"Experiments":[109],"performed":[115],"correspondingly":[116],"used":[120],"LibriSpeech,":[121],"GigaSpeech,":[122,139],"WavCaps,":[123],"AudioCaps,":[124],"Clotho":[126],"datasets":[127],"yield":[129],"results.":[131],"In":[132],"particular,":[133],"state-of-the-art":[134],"results":[135],"AudioCaps":[140],"Clotho.":[142],"Our":[143],"model":[144],"also":[146],"able":[147],"to":[148],"caption":[149],"simultaneously":[154],"from":[155],"clips":[156],"mixed":[158],"background":[161],"events,":[163],"which":[164],"step":[167],"towards":[168],"more":[169],"complete":[170],"machine":[171],"perception.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}