{"id":"https://openalex.org/W4385822532","doi":"https://doi.org/10.21437/interspeech.2023-619","title":"Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer","display_name":"Rethinking Transfer and Auxiliary Learning for Improving Audio Captioning Transformer","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822532","doi":"https://doi.org/10.21437/interspeech.2023-619"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-619","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5001866594","display_name":"Woo-Seok Shin","orcid":"https://orcid.org/0000-0002-8475-4795"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wooseok Shin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103110752","display_name":"Hyun Joon Park","orcid":"https://orcid.org/0000-0002-5308-6675"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyun Joon Park","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046518803","display_name":"Jin Sob Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin Sob Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030534867","display_name":"Dongwon Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongwon Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042820704","display_name":"Seung\u2010Jin Lee","orcid":"https://orcid.org/0000-0003-1255-0619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seungjin Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024995454","display_name":"Sung Won Han","orcid":"https://orcid.org/0000-0002-0040-3542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sung Won Han","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001866594"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6386,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84217673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2128","last_page":"2132"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.9962000250816345,"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":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9746999740600586,"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":0.9397000074386597,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7046101093292236},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6790512800216675},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.666681170463562},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4335663914680481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37448573112487793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22872129082679749},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1847703754901886},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17451685667037964}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7046101093292236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790512800216675},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.666681170463562},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4335663914680481},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37448573112487793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22872129082679749},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1847703754901886},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17451685667037964},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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:10.21437/interspeech.2023-619","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W4310447809","https://openalex.org/W4200243030","https://openalex.org/W2800782462","https://openalex.org/W4323777661","https://openalex.org/W3209117276","https://openalex.org/W4388184981"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-03T06:13:14.889584","created_date":"2025-10-10T00:00:00"}
