{"id":"https://openalex.org/W3187963534","doi":"https://doi.org/10.1109/icassp43922.2022.9747676","title":"Automated Audio Captioning Using Transfer Learning and Reconstruction Latent Space Similarity Regularization","display_name":"Automated Audio Captioning Using Transfer Learning and Reconstruction Latent Space Similarity Regularization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3187963534","doi":"https://doi.org/10.1109/icassp43922.2022.9747676","mag":"3187963534"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747676","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":"conference-paper","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/A5039185967","display_name":"Andrew Koh","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Andrew Koh","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097163779","display_name":"Xue Fuzhao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xue Fuzhao","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chng Eng Siong","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chng Eng Siong","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7722","last_page":"7726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7622984647750854},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.727724015712738},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6902928948402405},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6811632513999939},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6053329706192017},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5833746194839478},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5661756992340088},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.522864580154419},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5111690163612366},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5106592774391174},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47829633951187134},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46085280179977417},{"id":"https://openalex.org/keywords/similarity-learning","display_name":"Similarity learning","score":0.43458783626556396},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.41566604375839233},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39271432161331177},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3924773633480072},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33911681175231934},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3343130648136139},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09068262577056885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622984647750854},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.727724015712738},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6902928948402405},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6811632513999939},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6053329706192017},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5833746194839478},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5661756992340088},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.522864580154419},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5111690163612366},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5106592774391174},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47829633951187134},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46085280179977417},{"id":"https://openalex.org/C2779597229","wikidata":"https://www.wikidata.org/wiki/Q17146505","display_name":"Similarity learning","level":3,"score":0.43458783626556396},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.41566604375839233},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39271432161331177},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3924773633480072},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33911681175231934},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3343130648136139},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09068262577056885},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747676","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747676","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2506483933","https://openalex.org/W2626778328","https://openalex.org/W2896457183","https://openalex.org/W2936695845","https://openalex.org/W2936774411","https://openalex.org/W2945761034","https://openalex.org/W2949376505","https://openalex.org/W2951548327","https://openalex.org/W2952122856","https://openalex.org/W2964213897","https://openalex.org/W2996403597","https://openalex.org/W3015591594","https://openalex.org/W3016059657","https://openalex.org/W3033182893","https://openalex.org/W3094550259","https://openalex.org/W3112467147","https://openalex.org/W3135656708","https://openalex.org/W3160577380","https://openalex.org/W3185739472","https://openalex.org/W4385245566","https://openalex.org/W6639102338","https://openalex.org/W6682631176","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6761205521","https://openalex.org/W6769635231","https://openalex.org/W6779136962","https://openalex.org/W6784377407","https://openalex.org/W6787564935","https://openalex.org/W6798955355","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W3088136942","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"examine":[4],"the":[5,27,34,57,60,64,67,83,91],"use":[6],"of":[7,59,74,82],"Transfer":[8],"Learning":[9],"using":[10],"Pretrained":[11],"Audio":[12,36],"Neural":[13],"Networks":[14],"(PANNs)":[15],"[1],":[16],"and":[17,69,98],"propose":[18],"an":[19],"architecture":[20],"that":[21],"is":[22],"able":[23],"to":[24,79],"better":[25],"leverage":[26],"acoustic":[28],"features":[29],"provided":[30],"by":[31,62,86],"PANNs":[32],"for":[33],"Automated":[35],"Captioning":[37],"Task":[38],"[2].":[39],"We":[40],"also":[41],"introduce":[42],"a":[43,87],"novel":[44],"self-supervised":[45],"objective,":[46],"Reconstruction":[47],"Latent":[48],"Space":[49],"Similarity":[50],"Regularization":[51],"(RLSSR).":[52],"The":[53,72],"RLSSR":[54],"module":[55],"supplements":[56],"training":[58],"model":[61],"maximizing":[63],"similarity":[65],"between":[66],"encoder":[68],"decoder":[70],"embedding.":[71],"combination":[73],"both":[75],"methods":[76],"allows":[77],"us":[78],"surpass":[80],"state":[81],"art":[84],"results":[85],"significant":[88],"margin":[89],"on":[90],"Clotho":[92],"dataset":[93],"[3]":[94],"across":[95],"several":[96],"metrics":[97],"benchmarks.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}