{"id":"https://openalex.org/W2935170919","doi":"https://doi.org/10.1109/icassp.2019.8683727","title":"Acoustic Scene Generation with Conditional Samplernn","display_name":"Acoustic Scene Generation with Conditional Samplernn","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2935170919","doi":"https://doi.org/10.1109/icassp.2019.8683727","mag":"2935170919"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5072482416","display_name":"Qiuqiang Kong","orcid":"https://orcid.org/0000-0003-2864-0475"},"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":"Qiuqiang Kong","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"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/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056441203","display_name":"Turab Iqbal","orcid":"https://orcid.org/0000-0003-3393-2544"},"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":"Turab Iqbal","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"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/A5101590005","display_name":"Yin Cao","orcid":"https://orcid.org/0000-0001-9086-7027"},"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":"Yin Cao","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"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/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":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"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/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":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"affiliations":[{"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":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072482416"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":1.5022,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.82722736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"2019","issue":null,"first_page":"925","last_page":"929"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9941999912261963,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9860000014305115,"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":0.7788270711898804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5900887250900269},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5838091969490051},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.525116503238678},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5151006579399109},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4969816505908966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4833340346813202},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4467580020427704},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.43569236993789673},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3247329294681549}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788270711898804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5900887250900269},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5838091969490051},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.525116503238678},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5151006579399109},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4969816505908966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4833340346813202},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4467580020427704},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.43569236993789673},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3247329294681549},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8683727","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683727","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.44SUR_INST:11139862210002346","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:epubs.surrey.ac.uk:850808","is_oa":false,"landing_page_url":"http://epubs.surrey.ac.uk/850808/1/Acoustic%20scene%20generation%20with%20conditional%20SampleRNN.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400680","display_name":"Surrey Research Insight Open Access (The University of Surrey)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28290843","host_organization_name":"University of Surrey","host_organization_lineage":["https://openalex.org/I28290843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"mag:3162314443","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902254694357993","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8995825145","display_name":null,"funder_award_id":"EP/N014111/1","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1909320841","https://openalex.org/W1969746716","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2095705004","https://openalex.org/W2099057450","https://openalex.org/W2099471712","https://openalex.org/W2157331557","https://openalex.org/W2267126114","https://openalex.org/W2423557781","https://openalex.org/W2519091744","https://openalex.org/W2566935005","https://openalex.org/W2584032004","https://openalex.org/W2771361008","https://openalex.org/W2885392124","https://openalex.org/W2888470020","https://openalex.org/W2953318193","https://openalex.org/W2963373786","https://openalex.org/W2963636093","https://openalex.org/W2963857374","https://openalex.org/W2964121744","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6639732818","https://openalex.org/W6674330103","https://openalex.org/W6674887261","https://openalex.org/W6718379498","https://openalex.org/W6732429163","https://openalex.org/W6754161993"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Acoustic":[0],"scene":[1,107],"generation":[2],"(ASG)":[3],"is":[4,42,56],"a":[5,53,66,116,129,144,167],"task":[6],"to":[7,17,46,64,70,84,125,158],"generate":[8,18,71],"waveforms":[9],"for":[10,21,35],"acoustic":[11,72,106],"scenes.":[12],"ASG":[13,41],"can":[14,121],"be":[15,122],"used":[16,34],"audio":[19,114],"scenes":[20,73],"movies":[22],"and":[23,37,88,134],"computer":[24],"games.":[25],"Recently,":[26],"neural":[27],"networks":[28],"such":[29],"as":[30,156],"SampleRNN":[31,68],"have":[32],"been":[33],"speech":[36],"music":[38],"generation.":[39],"However,":[40],"more":[43],"challenging":[44],"due":[45],"its":[47],"wide":[48],"variety.":[49],"In":[50,59],"addition,":[51],"evaluating":[52],"generative":[54],"model":[55,69,131],"also":[57,80],"difficult.":[58],"this":[60],"paper,":[61],"we":[62],"propose":[63,81],"use":[65],"conditional":[67],"conditioned":[74],"on":[75,95,100,148],"the":[76,86,91,101,112],"input":[77],"classes.":[78],"We":[79],"objective":[82],"criteria":[83],"evaluate":[85],"quality":[87],"diversity":[89],"of":[90,119,132,139,143,154,161],"generated":[92,113,127,149,165],"samples":[93,126,135,150,164],"based":[94],"classification":[96,117],"accuracy.":[97],"The":[98,141],"experiments":[99],"DCASE":[102],"2016":[103],"Task":[104],"1":[105],"data":[108],"show":[109],"that":[110],"with":[111,163],"samples,":[115],"accuracy":[118,153,160],"65.5%":[120],"achieved":[123],"compared":[124],"by":[128,166],"random":[130,168],"6.7%":[133,162],"from":[136],"real":[137],"recording":[138],"83.1%.":[140],"performance":[142],"classifier":[145],"trained":[146],"only":[147],"achieves":[151],"an":[152,159],"51.3%,":[155],"opposed":[157],"model.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}