{"id":"https://openalex.org/W4407601448","doi":"https://doi.org/10.1145/3709026.3709118","title":"Improving Automated Audio Captioning with LLM Decoder and BEATs Audio Encoder","display_name":"Improving Automated Audio Captioning with LLM Decoder and BEATs Audio Encoder","publication_year":2024,"publication_date":"2024-12-06","ids":{"openalex":"https://openalex.org/W4407601448","doi":"https://doi.org/10.1145/3709026.3709118"},"language":"en","primary_location":{"id":"doi:10.1145/3709026.3709118","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3709026.3709118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence","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/A5119246606","display_name":"White Z.H. Liu","orcid":"https://orcid.org/0000-0003-1014-7244"},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weizhuo Liu","raw_affiliation_strings":["The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, ShangHai, ShangHai, China"],"affiliations":[{"raw_affiliation_string":"The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, ShangHai, ShangHai, China","institution_ids":["https://openalex.org/I21945476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016484039","display_name":"\u54f2\u96c4 \u65e5\u9ad8","orcid":null},"institutions":[{"id":"https://openalex.org/I21945476","display_name":"Shanghai Normal University","ror":"https://ror.org/01cxqmw89","country_code":"CN","type":"education","lineage":["https://openalex.org/I21945476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Gao","raw_affiliation_strings":["The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, ShangHai, ShangHai, China"],"affiliations":[{"raw_affiliation_string":"The College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, ShangHai, ShangHai, China","institution_ids":["https://openalex.org/I21945476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119246606"],"corresponding_institution_ids":["https://openalex.org/I21945476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30934693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"259"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9984999895095825,"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/T10860","display_name":"Speech and Audio Processing","score":0.996399998664856,"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/computer-science","display_name":"Computer science","score":0.8144643306732178},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7215526103973389},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6078566312789917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5738164782524109},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5359756350517273},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.34246116876602173},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3224457800388336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15631908178329468},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0860680341720581}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144643306732178},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7215526103973389},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6078566312789917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5738164782524109},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5359756350517273},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.34246116876602173},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3224457800388336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15631908178329468},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0860680341720581},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3709026.3709118","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3709026.3709118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W2506483933","https://openalex.org/W2593116425","https://openalex.org/W2612690371","https://openalex.org/W2949376505","https://openalex.org/W2970641574","https://openalex.org/W3015591594","https://openalex.org/W3034999214","https://openalex.org/W3094550259","https://openalex.org/W3103022576","https://openalex.org/W3196974791","https://openalex.org/W3205644108","https://openalex.org/W3205860970","https://openalex.org/W3209984917","https://openalex.org/W4377086529","https://openalex.org/W4387609319","https://openalex.org/W4392903033"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W1911859126","https://openalex.org/W2363440576","https://openalex.org/W2120730869","https://openalex.org/W1569721167","https://openalex.org/W2541680182","https://openalex.org/W2166699153"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
