{"id":"https://openalex.org/W4404037473","doi":"https://doi.org/10.1109/mlsp58920.2024.10734745","title":"Investigating Passive Filter Pruning for Efficient CNN-Transformer Audio Captioning","display_name":"Investigating Passive Filter Pruning for Efficient CNN-Transformer Audio Captioning","publication_year":2024,"publication_date":"2024-09-22","ids":{"openalex":"https://openalex.org/W4404037473","doi":"https://doi.org/10.1109/mlsp58920.2024.10734745"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp58920.2024.10734745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp58920.2024.10734745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","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,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/A5059302295","display_name":"Arshdeep Singh","orcid":"https://orcid.org/0000-0003-3465-0952"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arshdeep Singh","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"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,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/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK"],"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025827045"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.7501,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71501231,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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/T11309","display_name":"Music and Audio Processing","score":0.9871000051498413,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9679999947547913,"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":0.7965108156204224},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7320221662521362},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6491831541061401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5264202952384949},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.43521595001220703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27795010805130005},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2113344967365265},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14044764637947083},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12209692597389221},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05627050995826721}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7965108156204224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7320221662521362},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6491831541061401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5264202952384949},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.43521595001220703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27795010805130005},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2113344967365265},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14044764637947083},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12209692597389221},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05627050995826721},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp58920.2024.10734745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp58920.2024.10734745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 34th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6399999856948853,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2285660444","https://openalex.org/W2805003733","https://openalex.org/W2928560789","https://openalex.org/W3028304412","https://openalex.org/W3034513523","https://openalex.org/W3043781581","https://openalex.org/W3139123974","https://openalex.org/W3184606595","https://openalex.org/W3198452188","https://openalex.org/W3205708381","https://openalex.org/W3205860970","https://openalex.org/W4221150524","https://openalex.org/W4296070204","https://openalex.org/W4372260058","https://openalex.org/W4372269499","https://openalex.org/W4385822750","https://openalex.org/W4385822843","https://openalex.org/W4386764067","https://openalex.org/W4389240720","https://openalex.org/W4400033239","https://openalex.org/W6726275242","https://openalex.org/W6761068022","https://openalex.org/W6762718338","https://openalex.org/W6763563303","https://openalex.org/W6780864004","https://openalex.org/W6792390701","https://openalex.org/W6809947431"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W3209117276","https://openalex.org/W4388184981","https://openalex.org/W4323777661"],"abstract_inverted_index":{"Although":[0],"automated":[1],"audio":[2,48,57],"captioning":[3],"(AAC)":[4],"has":[5,38],"achieved":[6],"remarkable":[7],"performance":[8],"improvement":[9],"in":[10,47],"recent":[11],"years,":[12],"concerns":[13],"about":[14],"the":[15,25,30,54,75,96,102,108,111,119,128],"complexity":[16],"of":[17,32,77,127],"AAC":[18,87],"models":[19],"have":[20],"drawn":[21],"little":[22],"attention":[23],"from":[24,101],"research":[26],"community.":[27],"To":[28],"reduce":[29],"number":[31,121],"model":[33,117,130],"parameters,":[34],"passive":[35,79],"filter":[36,80],"pruning":[37,62,81,98,100,113],"been":[39],"successfully":[40],"applied":[41],"to":[42,53,125],"convolution":[43,104],"neural":[44],"networks":[45],"(CNNs)":[46],"classification":[49,58],"tasks.":[50],"However,":[51],"due":[52],"discrepancy":[55],"between":[56],"and":[59],"AAC,":[60],"these":[61],"methods":[63],"are":[64],"not":[65],"necessarily":[66],"suitable":[67],"for":[68],"captioning.":[69],"In":[70],"this":[71],"work,":[72],"we":[73,92],"investigate":[74],"effectiveness":[76],"several":[78],"approaches":[82],"on":[83],"an":[84],"efficient":[85],"CNN-Transformer-based":[86],"architecture.":[88],"Through":[89],"extensive":[90],"experiments,":[91],"find":[93],"that":[94,126],"under":[95],"same":[97],"ratio,":[99],"later":[103],"blocks":[105],"significantly":[106],"improves":[107],"performance.":[109,135],"Utilizing":[110],"norm-based":[112],"method,":[114],"our":[115],"pruned":[116],"reduces":[118],"parameter":[120],"by":[122],"15%":[123],"compared":[124],"original":[129],"while":[131],"maintaining":[132],"a":[133],"similar":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}