{"id":"https://openalex.org/W4405709413","doi":"https://doi.org/10.1109/iscslp63861.2024.10800334","title":"Vivid Background Audio Generation Based on Large Language Models and AudioLDM","display_name":"Vivid Background Audio Generation Based on Large Language Models and AudioLDM","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405709413","doi":"https://doi.org/10.1109/iscslp63861.2024.10800334"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10800334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101246571","display_name":"Yiwei Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiwei Liang","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100780143","display_name":"Ming Li","orcid":"https://orcid.org/0009-0009-3842-7337"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Data Science Research Center,Kunshan","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101246571"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27106757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"625"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9531999826431274,"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":0.9531999826431274,"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":0.7392514944076538},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4336322247982025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4271194636821747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.390379399061203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392514944076538},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4336322247982025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4271194636821747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.390379399061203}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp63861.2024.10800334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10800334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W4205501626","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4372262418","https://openalex.org/W4377010269","https://openalex.org/W4382246105","https://openalex.org/W4396877837","https://openalex.org/W6847038466","https://openalex.org/W6847076894","https://openalex.org/W6849109464","https://openalex.org/W6853937136"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3,26],"background":[4,32,44,65,116,131],"audio":[5,45,66,85,132],"and":[6,13,41,67,109,114,127,138],"speech":[7,29,112,136],"generation":[8],"system":[9,20],"for":[10],"the":[11,42,53,60,72,75,83,107,119,130],"Inspirational":[12],"Convincing":[14],"Audio":[15],"Gener-ation":[16],"Challenge":[17],"2024.":[18],"Our":[19],"mainly":[21],"includes":[22],"three":[23],"modules,":[24],"namely,":[25],"text-to-speech":[27],"(TTS),":[28],"synthesis":[30],"base-line,":[31],"text":[33,56,113,137],"description":[34,57,88],"extraction":[35,58,89],"based":[36,47],"on":[37,48,59,82],"large":[38,79,141],"language":[39,80,142],"models,":[40],"corresponding":[43,69],"gener-ation":[46],"latent":[49],"diffusion.":[50],"We":[51,92],"compare":[52],"influence":[54],"of":[55,62,77],"degree":[61],"correlation":[63],"between":[64,111],"its":[68,115],"speech.":[70],"At":[71],"same":[73],"time,":[74],"results":[76],"different":[78],"models":[81,126,143],"back-ground":[84],"generated":[86,133],"after":[87],"are":[90],"compared.":[91],"also":[93],"propose":[94],"an":[95],"alternative":[96],"evaluation":[97,121],"metric":[98],"named":[99],"Overall":[100],"Correlation":[101],"Quality":[102],"Score":[103],"(OCQS)":[104],"to":[105],"evaluate":[106],"rele-vance":[108],"naturalness":[110],"audio.":[117],"With":[118],"above":[120],"metric,":[122],"we":[123],"test":[124],"multiple":[125],"find":[128],"that":[129],"by":[134,140],"extracted":[135],"summarized":[139],"achieve":[144],"better":[145],"quality.":[146]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}