{"id":"https://openalex.org/W4375869093","doi":"https://doi.org/10.1109/icassp49357.2023.10096328","title":"Towards Controllable Audio Texture Morphing","display_name":"Towards Controllable Audio Texture Morphing","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869093","doi":"https://doi.org/10.1109/icassp49357.2023.10096328"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5016367573","display_name":"Chitralekha Gupta","orcid":"https://orcid.org/0000-0003-1350-9095"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chitralekha Gupta","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038084030","display_name":"Purnima Kamath","orcid":"https://orcid.org/0000-0003-0351-6574"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Purnima Kamath","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088301492","display_name":"Yize Wei","orcid":"https://orcid.org/0009-0004-3124-6975"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yize Wei","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066542435","display_name":"Zhuoyao Li","orcid":"https://orcid.org/0000-0003-0295-0897"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhuoyao Li","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027647989","display_name":"Suranga Nanayakkara","orcid":"https://orcid.org/0000-0001-7441-5493"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Suranga Nanayakkara","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062692118","display_name":"Lonce Wyse","orcid":"https://orcid.org/0000-0002-9200-1048"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Lonce Wyse","raw_affiliation_strings":["Universitat Pompeu Fabra,Barcelona,Spain","Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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":0.9972000122070312,"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/morphing","display_name":"Morphing","score":0.9496257305145264},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7634425759315491},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.5886676907539368},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.48890629410743713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4788091778755188},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4300241470336914},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.41446414589881897},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.4125213623046875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40293416380882263},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34651386737823486},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3395844101905823},{"id":"https://openalex.org/keywords/image-texture","display_name":"Image texture","score":0.23677262663841248},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.202558696269989},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.10236606001853943},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.086416095495224}],"concepts":[{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.9496257305145264},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634425759315491},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.5886676907539368},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.48890629410743713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4788091778755188},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4300241470336914},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.41446414589881897},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.4125213623046875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40293416380882263},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34651386737823486},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3395844101905823},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.23677262663841248},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.202558696269989},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.10236606001853943},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.086416095495224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096328","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096328","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W353758939","https://openalex.org/W2062663442","https://openalex.org/W2108598243","https://openalex.org/W2150307531","https://openalex.org/W2396187157","https://openalex.org/W2516594951","https://openalex.org/W2606176153","https://openalex.org/W2910577860","https://openalex.org/W2938577267","https://openalex.org/W2964193438","https://openalex.org/W2989955315","https://openalex.org/W3015856896","https://openalex.org/W3045062880","https://openalex.org/W3103301587","https://openalex.org/W3118215210","https://openalex.org/W3121122991","https://openalex.org/W3135377667","https://openalex.org/W4226088658","https://openalex.org/W4283027738","https://openalex.org/W4287271111","https://openalex.org/W4288043632","https://openalex.org/W4293253667","https://openalex.org/W6612017696","https://openalex.org/W6683590716","https://openalex.org/W6736723571","https://openalex.org/W6758675244","https://openalex.org/W6765147365","https://openalex.org/W6781150751","https://openalex.org/W6785870135","https://openalex.org/W6790986643","https://openalex.org/W6791852959","https://openalex.org/W6799832425","https://openalex.org/W6841297692","https://openalex.org/W6842854468"],"related_works":["https://openalex.org/W44139278","https://openalex.org/W62370349","https://openalex.org/W2289868279","https://openalex.org/W4315836293","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2970176078","https://openalex.org/W1975359510","https://openalex.org/W2098934641","https://openalex.org/W4387698063"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,10,29,73,94,97],"data-driven":[6,99],"approach":[7,70,100],"to":[8,64,101],"train":[9],"Generative":[11],"Adversarial":[12],"Network":[13],"(GAN)":[14],"conditioned":[15],"on":[16,28],"\"soft-labels\"":[17],"distilled":[18],"from":[19],"the":[20,50,65,86,89],"penultimate":[21],"layer":[22],"of":[23,32,88,110],"an":[24],"audio":[25,33,52,59,80,104],"classifier":[26],"trained":[27],"target":[30],"set":[31],"texture":[34,60],"classes.":[35],"We":[36],"demonstrate":[37],"that":[38,77],"interpolation":[39],"between":[40,49],"such":[41],"conditions":[42],"or":[43,57],"control":[44],"vectors":[45],"provide":[46],"smooth":[47],"morphing":[48,61],"generated":[51],"textures,":[53],"and":[54],"show":[55],"similar":[56],"better":[58],"capability":[62],"compared":[63],"state-of-the-art":[66],"methods.":[67],"The":[68],"proposed":[69],"results":[71],"in":[72],"well-organized":[74],"latent":[75],"space":[76],"generates":[78],"novel":[79,115],"outputs":[81],"while":[82],"remaining":[83],"consistent":[84],"with":[85,106],"semantics":[87],"conditioning":[90],"parameters.":[91],"This":[92],"is":[93],"step":[95],"towards":[96],"general":[98],"designing":[102],"generative":[103],"models":[105],"customized":[107],"controls":[108],"capable":[109],"traversing":[111],"out-of-distribution":[112],"regions":[113],"for":[114],"sound":[116],"synthesis.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
