{"id":"https://openalex.org/W4388118236","doi":"https://doi.org/10.23919/eusipco58844.2023.10289975","title":"Leveraging Pre-Trained AudioLDM for Sound Generation: A Benchmark Study","display_name":"Leveraging Pre-Trained AudioLDM for Sound Generation: A Benchmark Study","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388118236","doi":"https://doi.org/10.23919/eusipco58844.2023.10289975"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289975","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5101889011","display_name":"Yi Yuan","orcid":"https://orcid.org/0000-0002-7121-0983"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yi Yuan","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100526373","display_name":"Jinhua Liang","orcid":"https://orcid.org/0000-0002-4570-0735"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinhua Liang","raw_affiliation_strings":["Queen Mary University of London,Centre for Digital Music (C4DM)","Centre for Digital Music (C4DM), Queen Mary University of London"],"affiliations":[{"raw_affiliation_string":"Queen Mary University of London,Centre for Digital Music (C4DM)","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Centre for Digital Music (C4DM), Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407730","display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),UK","institution_ids":["https://openalex.org/I28290843"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101889011"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.2405,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80584645,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"765","last_page":"769"},"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":0.9990000128746033,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7807655334472656},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7665432095527649},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5550628900527954},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5309504866600037},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4536903500556946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4260205030441284},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41821303963661194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3905959129333496},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3750045895576477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10020005702972412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807655334472656},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7665432095527649},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5550628900527954},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5309504866600037},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4536903500556946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4260205030441284},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41821303963661194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3905959129333496},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3750045895576477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10020005702972412},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289975","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7041590781","display_name":null,"funder_award_id":"202208060240","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"},{"id":"https://openalex.org/G8857457899","display_name":null,"funder_award_id":"EP/T019751/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2138857742","https://openalex.org/W2593116425","https://openalex.org/W2752796333","https://openalex.org/W2912237282","https://openalex.org/W2935170919","https://openalex.org/W2963373786","https://openalex.org/W2963799213","https://openalex.org/W3034999214","https://openalex.org/W3036167779","https://openalex.org/W3094550259","https://openalex.org/W3105017218","https://openalex.org/W3166396011","https://openalex.org/W3207498282","https://openalex.org/W3214281017","https://openalex.org/W4221155904","https://openalex.org/W4221157007","https://openalex.org/W4224871700","https://openalex.org/W4280561221","https://openalex.org/W4288089799","https://openalex.org/W4289106098","https://openalex.org/W4300980117","https://openalex.org/W4301206121","https://openalex.org/W4312898271","https://openalex.org/W4318718996","https://openalex.org/W4318752004","https://openalex.org/W4320165422","https://openalex.org/W4320342468","https://openalex.org/W4367359628","https://openalex.org/W4402536261","https://openalex.org/W6637373629","https://openalex.org/W6680300913","https://openalex.org/W6718379498","https://openalex.org/W6734260513","https://openalex.org/W6757220786","https://openalex.org/W6758930985","https://openalex.org/W6761002388","https://openalex.org/W6765779288","https://openalex.org/W6769311223","https://openalex.org/W6769627184","https://openalex.org/W6771438384","https://openalex.org/W6779823529","https://openalex.org/W6785633228","https://openalex.org/W6791353385","https://openalex.org/W6802805937","https://openalex.org/W6809935603","https://openalex.org/W6838721020","https://openalex.org/W6839857308","https://openalex.org/W6845479124","https://openalex.org/W6849109464","https://openalex.org/W6849416043","https://openalex.org/W6849693668","https://openalex.org/W6849801620","https://openalex.org/W6850275875"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204","https://openalex.org/W1492295194"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"have":[3],"recently":[4],"achieved":[5],"break-throughs":[6],"in":[7,67],"sound":[8,16,44,78,96,102,126],"generation.":[9,127],"Despite":[10],"the":[11,34,39,48,55,60,63,72,101],"outstanding":[12],"sample":[13],"quality,":[14],"current":[15],"generation":[17,45,79,97,103],"models":[18],"face":[19],"issues":[20],"on":[21,43,95,105,113,124],"small-scale":[22],"datasets":[23],"(e.g.,":[24],"overfitting),":[25],"significantly":[26],"limiting":[27],"performance.":[28],"In":[29,70],"this":[30],"paper,":[31],"we":[32,99],"make":[33],"first":[35],"attempt":[36],"to":[37,85,91],"investigate":[38],"benefits":[40],"of":[41,62],"pre-training":[42],"with":[46],"AudioLDM,":[47,65],"cutting-edge":[49],"model":[50],"for":[51,77,121],"audio":[52],"generation,":[53],"as":[54],"backbone.":[56],"Our":[57],"study":[58,94],"demonstrates":[59],"advantages":[61],"pre-trained":[64],"especially":[66],"data-scarcity":[68],"scenarios.":[69],"addition,":[71],"baselines":[73],"and":[74,116],"evaluation":[75],"protocol":[76],"systems":[80],"are":[81],"not":[82],"consistent":[83],"enough":[84],"compare":[86],"different":[87],"studies":[88],"directly.":[89],"Aiming":[90],"facilitate":[92],"further":[93,122],"tasks,":[98],"benchmark":[100],"task":[104],"various":[106],"frequently-used":[107],"datasets.":[108],"We":[109],"hope":[110],"our":[111],"results":[112],"transfer":[114],"learning":[115],"benchmarks":[117],"can":[118],"provide":[119],"references":[120],"research":[123],"conditional":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}