{"id":"https://openalex.org/W4416403626","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00268","title":"Personalized Conversational Audio Descriptions in 360\u00b0 Virtual Reality for Blind and Low-Vision Users","display_name":"Personalized Conversational Audio Descriptions in 360\u00b0 Virtual Reality for Blind and Low-Vision Users","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4416403626","doi":"https://doi.org/10.1109/ismar-adjunct68609.2025.00268"},"language":null,"primary_location":{"id":"doi:10.1109/ismar-adjunct68609.2025.00268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","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/A5040254449","display_name":"Khang Dang","orcid":"https://orcid.org/0000-0003-3481-497X"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khang Dang","raw_affiliation_strings":["New Jersey Institute of Technology"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063377877","display_name":"Sooyeon Lee","orcid":"https://orcid.org/0000-0002-3621-1868"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sooyeon Lee","raw_affiliation_strings":["New Jersey Institute of Technology"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040254449"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37109508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"961","last_page":"962"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.5357999801635742,"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":0.5357999801635742,"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/T10860","display_name":"Speech and Audio Processing","score":0.16459999978542328,"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/T13310","display_name":"Subtitles and Audiovisual Media","score":0.03959999978542328,"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/virtual-reality","display_name":"Virtual reality","score":0.6060000061988831},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5504000186920166},{"id":"https://openalex.org/keywords/narrative","display_name":"Narrative","score":0.5},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4237000048160553},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38499999046325684},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.3840999901294708},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.3116999864578247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641000151634216},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6545000076293945},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.6060000061988831},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.603600025177002},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C199033989","wikidata":"https://www.wikidata.org/wiki/Q1318295","display_name":"Narrative","level":2,"score":0.5},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4237000048160553},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C2983409430","wikidata":"https://www.wikidata.org/wiki/Q7935065","display_name":"Virtual agent","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C201025465","wikidata":"https://www.wikidata.org/wiki/Q11248500","display_name":"User experience design","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ismar-adjunct68609.2025.00268","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ismar-adjunct68609.2025.00268","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W3160237369","https://openalex.org/W4307475429","https://openalex.org/W4387611602","https://openalex.org/W4387793209","https://openalex.org/W4403576862","https://openalex.org/W4403576928","https://openalex.org/W4403576931","https://openalex.org/W4409720336","https://openalex.org/W4411469874","https://openalex.org/W4412035401","https://openalex.org/W4412055633"],"related_works":[],"abstract_inverted_index":{"On-demand,":[0],"conversational":[1],"audio":[2,56],"descriptions":[3],"in":[4],"360\u00b0":[5],"VR":[6,65,85],"empower":[7],"blind":[8],"and":[9,32,83],"low-vision":[10],"users":[11],"to":[12,39,53],"actively":[13],"explore":[14],"immersive":[15],"visual":[16],"content.":[17],"We":[18],"present":[19],"a":[20],"Meta":[21],"Quest":[22],"demo":[23],"that":[24],"integrates":[25],"head-pose-based":[26],"view":[27],"snapshots,":[28],"real-time":[29],"speech":[30],"recognition,":[31],"GPT-4o-powered":[33],"chunked":[34],"text-to-speech":[35],"streaming":[36],"directly":[37],"on-device":[38],"support":[40],"multi-turn":[41],"Q&A":[42],"with":[43],"personalized":[44],"voice":[45],"profiles.":[46],"Our":[47],"pipeline":[48],"leverages":[49],"chunk":[50],"transfer":[51],"encoding":[52],"play":[54],"AI-generated":[55],"as":[57],"it\u2019s":[58],"produced,":[59],"minimizing":[60],"perceived":[61],"delay.":[62],"Unlike":[63],"prior":[64],"accessibility":[66],"demos":[67],"reliant":[68],"on":[69],"static":[70],"or":[71],"author-crafted":[72],"descriptions,":[73],"our":[74],"multimodal":[75],"system":[76],"delivers":[77],"dynamic,":[78],"user-driven":[79],"narration":[80],"for":[81],"inclusive":[82],"interactive":[84],"experiences.":[86]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-18T00:00:00"}
