{"id":"https://openalex.org/W7147057995","doi":"https://doi.org/10.1145/3772318.3791655","title":"Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes","display_name":"Beyond Descriptions: A Generative Scene2Audio Framework for Blind and Low-Vision Users to Experience Vista Landscapes","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7147057995","doi":"https://doi.org/10.1145/3772318.3791655"},"language":"en","primary_location":{"id":"doi:10.1145/3772318.3791655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791655","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3772318.3791655","any_repository_has_fulltext":true},"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":["Augmented Human Lab, Dept. of Computer Science, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-1350-9095","affiliations":[{"raw_affiliation_string":"Augmented Human Lab, Dept. of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132654199","display_name":"Jing Peng","orcid":null},"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":"Jing Peng","raw_affiliation_strings":["Augmented Human Lab, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-4054-3547","affiliations":[{"raw_affiliation_string":"Augmented Human Lab, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112255485","display_name":"Ashwin N. Ram","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ashwin Ram","raw_affiliation_strings":["Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1430-8770","affiliations":[{"raw_affiliation_string":"Saarland University, Saarland Informatics Campus, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074844108","display_name":"S. Sridhar","orcid":"https://orcid.org/0009-0004-6675-3459"},"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":"Shreyas Sridhar","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-6675-3459","affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132616013","display_name":"Christophe Jouffrais","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555"]},{"id":"https://openalex.org/I3131550300","display_name":"Universit\u00e9 Toulouse-I-Capitole","ror":"https://ror.org/0443n9e75","country_code":"FR","type":"education","lineage":["https://openalex.org/I3131550300"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I4210152422","display_name":"Universit\u00e9 Toulouse - Jean Jaur\u00e8s","ror":"https://ror.org/04ezk3x31","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210152422"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Christophe Jouffrais","raw_affiliation_strings":["IRIT, CNRS, Toulouse, France and IPAL, CNRS, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-0768-1019","affiliations":[{"raw_affiliation_string":"IRIT, CNRS, Toulouse, France and IPAL, CNRS, Singapore, Singapore","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I134560555","https://openalex.org/I3131550300","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4210160189"]}]},{"author_position":"last","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":["Augmented Human Lab, School of Computing, National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7441-5493","affiliations":[{"raw_affiliation_string":"Augmented Human Lab, School of Computing, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.8198000192642212,"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"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.8198000192642212,"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/T12032","display_name":"Multisensory perception and integration","score":0.08820000290870667,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13310","display_name":"Subtitles and Audiovisual Media","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"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/perception","display_name":"Perception","score":0.6710000038146973},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5612999796867371},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41940000653266907},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3880000114440918},{"id":"https://openalex.org/keywords/nonverbal-communication","display_name":"Nonverbal communication","score":0.3752000033855438},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.35690000653266907},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.3343999981880188}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6710000038146973},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5315999984741211},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4936999976634979},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41940000653266907},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3880000114440918},{"id":"https://openalex.org/C145633318","wikidata":"https://www.wikidata.org/wiki/Q207125","display_name":"Nonverbal communication","level":2,"score":0.3752000033855438},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.3343999981880188},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3237000107765198},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3190999925136566},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3037000000476837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C200220432","wikidata":"https://www.wikidata.org/wiki/Q7936208","display_name":"Vision science","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3772318.3791655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791655","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2603.27295","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.27295","pdf_url":"https://arxiv.org/pdf/2603.27295","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-05598965v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05598965","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"CHI '26, Apr 2026, Barcelone, Spain. pp.1 - 23, &#x27E8;10.1145/3772318.3791655&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3772318.3791655","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3772318.3791655","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Current":[0],"scene":[1,46,82,109,120],"perception":[2,121],"tools":[3],"for":[4,95],"Blind":[5],"and":[6,33,43,118],"Low":[7],"Vision":[8],"(BLV)":[9],"individuals":[10],"rely":[11],"on":[12],"spoken":[13],"descriptions":[14],"but":[15],"lack":[16],"engaging":[17],"representations":[18],"of":[19,45,104,132],"visually":[20],"pleasing":[21],"distant":[22],"environmental":[23],"landscapes":[24],"(Vista":[25],"spaces).":[26],"Our":[27,111],"proposed":[28],"Scene2Audio":[29,62,105],"framework":[30],"generates":[31],"comprehensible":[32],"enjoyable":[34],"nonverbal":[35],"audio":[36,47],"using":[37],"generative":[38],"models":[39],"informed":[40],"by":[41,122],"psychoacoustics,":[42],"principles":[44],"composition.":[48],"Through":[49],"a":[50,67,98],"user":[51],"study":[52,90],"with":[53,64,91],"11":[54],"BLV":[55,93,133],"participants,":[56],"we":[57],"found":[58],"that":[59],"combining":[60],"the":[61,74,78,81,102,114,129],"sounds":[63],"speech":[65,71,79],"creates":[66],"better":[68],"experience":[69],"than":[70,97],"alone,":[72],"as":[73],"sound":[75],"effects":[76],"complement":[77],"making":[80],"easier":[83],"to":[84],"imagine.":[85],"A":[86],"mobile":[87],"app":[88],"\u201cin-the-wild\u201d":[89],"7":[92],"users":[94],"more":[96],"week":[99],"further":[100],"showed":[101],"potential":[103],"in":[106],"enhancing":[107],"outdoor":[108],"experiences.":[110],"work":[112],"bridges":[113],"gap":[115],"between":[116],"visual":[117],"auditory":[119],"moving":[123],"beyond":[124],"purely":[125],"descriptive":[126],"aids,":[127],"addressing":[128],"aesthetic":[130],"needs":[131],"users.":[134]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-04-02T00:00:00"}
