{"id":"https://openalex.org/W4402112418","doi":"https://doi.org/10.21437/interspeech.2024-65","title":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","display_name":"Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112418","doi":"https://doi.org/10.21437/interspeech.2024-65"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-65","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-65","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5027021954","display_name":"Jizhong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jizhong Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018012012","display_name":"Gang Li","orcid":"https://orcid.org/0000-0002-8573-1608"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113948981","display_name":"Zhiyong Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107061814","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0003-1118-3618"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1135","last_page":"1139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9781000018119812,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9559000134468079,"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":0.8146569132804871},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8071181774139404},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7816191911697388},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45398348569869995},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4426501393318176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21797212958335876},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07182136178016663}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146569132804871},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8071181774139404},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7816191911697388},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45398348569869995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4426501393318176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21797212958335876},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07182136178016663}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-65","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-65","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W1911859126","https://openalex.org/W2120730869","https://openalex.org/W2166699153","https://openalex.org/W2541680182"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
