{"id":"https://openalex.org/W4372259880","doi":"https://doi.org/10.1109/icassp49357.2023.10094866","title":"Autonomous Soundscape Augmentation with Multimodal Fusion of Visual and Participant-Linked Inputs","display_name":"Autonomous Soundscape Augmentation with Multimodal Fusion of Visual and Participant-Linked Inputs","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372259880","doi":"https://doi.org/10.1109/icassp49357.2023.10094866"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094866","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":"preprint","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/A5086986606","display_name":"Kenneth Ooi","orcid":"https://orcid.org/0000-0001-5629-6275"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Kenneth Ooi","raw_affiliation_strings":["Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076817923","display_name":"Karn N. Watcharasupat","orcid":"https://orcid.org/0000-0002-3878-5048"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karn N. Watcharasupat","raw_affiliation_strings":["Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA","Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Center for Music Technology,Atlanta,GA,USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Music Technology, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027409015","display_name":"Bhan Lam","orcid":"https://orcid.org/0000-0001-5193-6560"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bhan Lam","raw_affiliation_strings":["Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029701603","display_name":"Zhen-Ting Ong","orcid":"https://orcid.org/0000-0002-1249-4760"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhen-Ting Ong","raw_affiliation_strings":["Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072584895","display_name":"Woon\u2010Seng Gan","orcid":"https://orcid.org/0000-0002-7143-1823"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Woon-Seng Gan","raw_affiliation_strings":["Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical and Electronic Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5086986606"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":3.06811572,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84971978,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T11692","display_name":"Noise Effects and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11692","display_name":"Noise Effects and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.7355548143386841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7013400793075562},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6789453029632568},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5415615439414978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5211041569709778},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.5208938121795654},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5103439688682556},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42731761932373047},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.420119047164917},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4049207866191864},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3678928017616272},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35071903467178345},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.06959721446037292}],"concepts":[{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.7355548143386841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013400793075562},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6789453029632568},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5415615439414978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211041569709778},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5208938121795654},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5103439688682556},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42731761932373047},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.420119047164917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4049207866191864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3678928017616272},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35071903467178345},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.06959721446037292},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094866","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094866","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"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/165017","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/165017","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1796012405","https://openalex.org/W1902237438","https://openalex.org/W1992226172","https://openalex.org/W2014438310","https://openalex.org/W2038266635","https://openalex.org/W2062632672","https://openalex.org/W2063634210","https://openalex.org/W2115195350","https://openalex.org/W2343999517","https://openalex.org/W2602348100","https://openalex.org/W2619383789","https://openalex.org/W2766432972","https://openalex.org/W2904546410","https://openalex.org/W2965144482","https://openalex.org/W2970527331","https://openalex.org/W2985581529","https://openalex.org/W3014709094","https://openalex.org/W3015427680","https://openalex.org/W3042478219","https://openalex.org/W3134858569","https://openalex.org/W3138077191","https://openalex.org/W3159296386","https://openalex.org/W3185617735","https://openalex.org/W4200341337","https://openalex.org/W4205240252","https://openalex.org/W4224932152","https://openalex.org/W4225323069","https://openalex.org/W4292994367","https://openalex.org/W4320183144","https://openalex.org/W4321487962","https://openalex.org/W6756881343","https://openalex.org/W6767532131","https://openalex.org/W6810514267","https://openalex.org/W6839533827"],"related_works":["https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W1988083194","https://openalex.org/W2282503792","https://openalex.org/W2365709658","https://openalex.org/W1562588264","https://openalex.org/W1593731728","https://openalex.org/W2970126706","https://openalex.org/W2770198033","https://openalex.org/W2809061312"],"abstract_inverted_index":{"Autonomous":[0],"soundscape":[1],"augmentation":[2,115],"systems":[3,116],"typically":[4],"use":[5],"trained":[6,135],"models":[7,136],"to":[8,12,23,44,51,96,137],"pick":[9],"optimal":[10],"maskers":[11],"effect":[13],"a":[14,87,97],"desired":[15],"perceptual":[16],"change.":[17],"While":[18],"acoustic":[19,37,63],"information":[20],"is":[21],"paramount":[22],"such":[24],"systems,":[25],"contextual":[26,80],"information,":[27],"including":[28],"participant":[29],"demographics":[30],"and":[31,55,62,70],"the":[32,75,83,92,104,111,128],"visual":[33],"environment,":[34],"also":[35,126],"influences":[36],"perception.":[38],"Hence,":[39],"we":[40],"propose":[41],"modular":[42],"modifications":[43],"an":[45],"existing":[46],"attention-based":[47],"deep":[48],"neural":[49],"network,":[50],"allow":[52],"early,":[53],"mid-level,":[54],"late":[56],"feature":[57],"fusion":[58,72],"of":[59,101,130],"participant-linked,":[60],"visual,":[61],"features.":[64],"Ablation":[65],"studies":[66],"on":[67,91],"module":[68],"configurations":[69],"corresponding":[71],"methods":[73],"using":[74,134],"ARAUS":[76],"dataset":[77],"show":[78],"that":[79],"features":[81],"improve":[82],"model":[84,141],"performance":[85],"in":[86,140],"statistically":[88],"significant":[89],"manner":[90],"normalized":[93],"ISO":[94],"Pleasantness,":[95],"mean":[98],"squared":[99],"error":[100],"0.1194\u00b10.0012":[102],"for":[103,110,122],"best-performing":[105],"all-modality":[106],"model,":[107],"against":[108],"0.1217\u00b10.0009":[109],"audio-only":[112],"model.":[113],"Soundscape":[114],"can":[117],"thereby":[118],"leverage":[119],"multimodal":[120],"inputs":[121],"improved":[123],"performance.":[124],"We":[125],"investigate":[127],"impact":[129],"individual":[131],"participant-linked":[132],"factors":[133],"illustrate":[138],"improvements":[139],"explainability.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
