{"id":"https://openalex.org/W3214281017","doi":"https://doi.org/10.1109/mlsp52302.2021.9596430","title":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","display_name":"Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3214281017","doi":"https://doi.org/10.1109/mlsp52302.2021.9596430","mag":"3214281017"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp52302.2021.9596430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"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":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,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/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","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,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/A5057816329","display_name":"Jinzheng Zhao","orcid":"https://orcid.org/0009-0004-3910-850X"},"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":"Jinzheng Zhao","raw_affiliation_strings":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,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/A5103097683","display_name":"Qiushi Huang","orcid":"https://orcid.org/0009-0004-1441-7090"},"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":"Qiushi Huang","raw_affiliation_strings":["University of Surrey,Department of Computer Science,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,Department of Computer Science,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":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,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":["Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,UK","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey,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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9977999925613403,"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":0.7655541896820068},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5774567127227783},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5577730536460876},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5565794110298157},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4907866418361664},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.47336050868034363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4386774003505707},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4219660460948944},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41885802149772644},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.1878272294998169},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11102619767189026},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08874312043190002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655541896820068},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5774567127227783},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5577730536460876},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5565794110298157},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4907866418361664},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.47336050868034363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4386774003505707},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4219660460948944},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41885802149772644},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.1878272294998169},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11102619767189026},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08874312043190002},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp52302.2021.9596430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp52302.2021.9596430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8600000143051147}],"awards":[{"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/F4320321979","display_name":"University of Surrey","ror":"https://ror.org/00ks66431"},{"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":39,"referenced_works":["https://openalex.org/W114355735","https://openalex.org/W1522301498","https://openalex.org/W1969746716","https://openalex.org/W2038484192","https://openalex.org/W2423557781","https://openalex.org/W2584032004","https://openalex.org/W2620812332","https://openalex.org/W2746068898","https://openalex.org/W2756983932","https://openalex.org/W2771361008","https://openalex.org/W2796101164","https://openalex.org/W2811079561","https://openalex.org/W2894295011","https://openalex.org/W2900801283","https://openalex.org/W2935170919","https://openalex.org/W2942415903","https://openalex.org/W2948211236","https://openalex.org/W2962942158","https://openalex.org/W2963403868","https://openalex.org/W2963428348","https://openalex.org/W2963557407","https://openalex.org/W2963609956","https://openalex.org/W2963636093","https://openalex.org/W2963799213","https://openalex.org/W2963804063","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2970881190","https://openalex.org/W3049446265","https://openalex.org/W3092028330","https://openalex.org/W3098403858","https://openalex.org/W3117290926","https://openalex.org/W3127705815","https://openalex.org/W4287329446","https://openalex.org/W4293568373","https://openalex.org/W4297817572","https://openalex.org/W4301837844","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W1590604789","https://openalex.org/W4393981309","https://openalex.org/W2792033502","https://openalex.org/W2170815394","https://openalex.org/W3043119899","https://openalex.org/W2159289746","https://openalex.org/W4394586068","https://openalex.org/W4254486954","https://openalex.org/W2296317756","https://openalex.org/W2065633372"],"abstract_inverted_index":{"Deep":[0],"generative":[1],"models":[2],"have":[3],"recently":[4],"achieved":[5],"impressive":[6],"performance":[7,123,141,147],"in":[8,48,57,97,142,148],"speech":[9],"and":[10,102,128,144],"music":[11],"synthesis.":[12],"However,":[13,52],"compared":[14,118],"to":[15,119],"the":[16,40,49,115,122,126],"generation":[17,47],"of":[18,71,130],"those":[19],"domain-specific":[20],"sounds,":[21],"generating":[22,81],"general":[23],"sounds":[24,62,82],"(such":[25],"as":[26,63],"siren,":[27],"gunshots)":[28],"has":[29],"received":[30],"less":[31],"attention,":[32],"despite":[33],"their":[34],"wide":[35],"applications.":[36],"In":[37,73],"previous":[38],"work,":[39,75],"SampleRNN":[41,53],"method":[42,79,138],"was":[43],"considered":[44],"for":[45,80],"sound":[46,91,108],"time":[50],"domain.":[51],"is":[54],"potentially":[55],"limited":[56,69],"capturing":[58],"long-range":[59,100],"dependencies":[60,101],"within":[61,107],"it":[64],"only":[65],"back-propagates":[66],"through":[67],"a":[68,78],"number":[70],"samples.":[72],"this":[74],"we":[76],"propose":[77],"via":[83],"neural":[84],"discrete":[85],"time-frequency":[86],"representation":[87],"learning,":[88],"conditioned":[89],"on":[90,114],"classes.":[92],"This":[93],"offers":[94,139],"an":[95],"advantage":[96],"efficiently":[98],"modelling":[99],"retaining":[103],"local":[104],"fine-grained":[105],"structures":[106],"clips.":[109],"We":[110],"evaluate":[111],"our":[112,137],"approach":[113],"UrbanSound8K":[116],"dataset,":[117],"SampleRNN,":[120],"with":[121],"metrics":[124],"measuring":[125],"quality":[127,143],"diversity":[129],"generated":[131],"sounds.":[132],"Experimental":[133],"results":[134],"show":[135],"that":[136],"comparable":[140],"significantly":[145],"better":[146],"diversity.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}