{"id":"https://openalex.org/W7044140646","doi":null,"title":"WavCraft: Audio Editing and Generation with Natural Language Prompts","display_name":"WavCraft: Audio Editing and Generation with Natural Language Prompts","publication_year":2024,"publication_date":"2024-03-14","ids":{"openalex":"https://openalex.org/W7044140646"},"language":"en","primary_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97150","doi":null,"is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liang, J","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, J","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, H","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, H","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, H","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, H","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cao, Y","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Y","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kong, Q","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Q","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, X","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, X","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, W","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, W","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Plumbley, MD","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Plumbley, MD","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X","observed_orcids":["https://orcid.org/0000-0003-4096-785X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phan, H","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Benetos, E","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benetos, E","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.8618000149726868,"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":0.8618000149726868,"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":0.094200000166893,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.017000000923871994,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-editing","display_name":"audio editing","score":0.9729999899864197},{"id":"https://openalex.org/keywords/audio-generation","display_name":"audio generation","score":0.9729999899864197},{"id":"https://openalex.org/keywords/natural-language-prompts","display_name":"natural language prompts","score":0.859000027179718},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9929999709129333},{"id":"https://openalex.org/keywords/task-decomposition","display_name":"task decomposition","score":0.7689999938011169},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.703000009059906},{"id":"https://openalex.org/keywords/audio-description","display_name":"audio description","score":0.5580000281333923},{"id":"https://openalex.org/keywords/dialogue-interaction","display_name":"dialogue interaction","score":0.7549999952316284},{"id":"https://openalex.org/keywords/user-control","display_name":"user control","score":0.5239999890327454},{"id":"https://openalex.org/keywords/audio-content-creation","display_name":"audio content creation","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381999731063843},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6539999842643738},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5566999912261963},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.49399998784065247},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4503999948501587},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.446399986743927},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.399399995803833},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.36959999799728394},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3434999883174896},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.3273000121116638},{"id":"https://openalex.org/C67463725","wikidata":"https://www.wikidata.org/wiki/Q17081452","display_name":"Natural language programming","level":5,"score":0.31150001287460327},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29319998621940613},{"id":"https://openalex.org/C2778488704","wikidata":"https://www.wikidata.org/wiki/Q15190726","display_name":"Audio equipment","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2775000035762787},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97150","doi":null,"is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97150","doi":null,"is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97150/2/Liang%20WavCraft%20audio%20editing%202024%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7044140646.pdf","grobid_xml":"https://content.openalex.org/works/W7044140646.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2593116425","https://openalex.org/W3205475937","https://openalex.org/W3208743843","https://openalex.org/W4313679638","https://openalex.org/W4318351475","https://openalex.org/W4318718936","https://openalex.org/W4323697341","https://openalex.org/W4377130946","https://openalex.org/W4377372369","https://openalex.org/W4381786045","https://openalex.org/W4384812233","https://openalex.org/W4390490761","https://openalex.org/W4390872747","https://openalex.org/W4393178509","https://openalex.org/W4400033239","https://openalex.org/W4402952465","https://openalex.org/W4404612934","https://openalex.org/W4405934446","https://openalex.org/W4406794295","https://openalex.org/W4410986283","https://openalex.org/W7133202489","https://openalex.org/W7133214447","https://openalex.org/W7133224126","https://openalex.org/W7133224691","https://openalex.org/W7133229781"],"related_works":["https://openalex.org/W4392873902","https://openalex.org/W4410986283","https://openalex.org/W7101796570","https://openalex.org/W7133224691","https://openalex.org/W7083685130","https://openalex.org/W4403901561","https://openalex.org/W4416017085","https://openalex.org/W7126268448","https://openalex.org/W7130719859","https://openalex.org/W4406794295"],"abstract_inverted_index":{"We":[0],"introduce":[1],"WavCraft,":[2],"a":[3,76,127,164],"collective":[4],"system":[5],"that":[6,124],"leverages":[7,47],"large":[8],"language":[9,34],"models":[10,16],"(LLMs)":[11],"to":[12,55,86,105,148],"connect":[13],"diverse":[14],"task-specific":[15,79],"for":[17],"audio":[18,30,41,90,116,140,152,161],"content":[19,27,91,117,153],"creation":[20],"and":[21,35,43,62,95,112,150],"editing.":[22],"Specifically,":[23],"WavCraft":[24,46,81,102,125,143],"describes":[25],"the":[26,37,48,53,68,83,115,136,155],"of":[28,52,78,139,157,167],"raw":[29],"materials":[31],"in":[32,163],"natural":[33],"prompts":[36],"LLM":[38,54],"conditioned":[39],"on":[40,154],"descriptions":[42],"user":[44,98,120],"requests.":[45],"in-context":[49],"learning":[50],"ability":[51],"decomposes":[56],"users'":[57],"instructions":[58,147],"into":[59],"several":[60],"tasks":[61],"tackle":[63],"each":[64],"task":[65,72],"collaboratively":[66],"with":[67,75,92,107],"particular":[69],"module.":[70],"Through":[71],"decomposition":[73],"along":[74],"set":[77],"models,":[80],"follows":[82],"input":[84,158],"instruction":[85],"create":[87,151],"or":[88],"edit":[89,149],"more":[93],"details":[94],"rationales,":[96],"facilitating":[97,160],"control.":[99],"In":[100],"addition,":[101],"is":[103],"able":[104],"cooperate":[106],"users":[108],"via":[109],"dialogue":[110],"interaction":[111],"even":[113],"produce":[114],"without":[118],"explicit":[119],"commands.":[121],"Experiments":[122],"demonstrate":[123],"yields":[126],"better":[128],"performance":[129],"than":[130],"existing":[131],"methods,":[132],"especially":[133],"when":[134],"adjusting":[135],"local":[137],"regions":[138],"clips.":[141],"Moreover,":[142],"can":[144],"follow":[145],"complex":[146],"top":[156],"recordings,":[159],"producers":[162],"broader":[165],"range":[166],"applications.":[168]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
