{"id":"https://openalex.org/W7153827888","doi":"https://doi.org/10.1145/3772363.3798425","title":"Sonic Stage: Automatically Generating an Interactive Spatial Soundscape to Facilitate Dialogue Video Comprehension for Blind and Low Vision Viewers","display_name":"Sonic Stage: Automatically Generating an Interactive Spatial Soundscape to Facilitate Dialogue Video Comprehension for Blind and Low Vision Viewers","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7153827888","doi":"https://doi.org/10.1145/3772363.3798425"},"language":"en","primary_location":{"id":"doi:10.1145/3772363.3798425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772363.3798425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","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/A5109800029","display_name":"Shuchang Xu","orcid":"https://orcid.org/0000-0002-7642-9044"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuchang Xu","raw_affiliation_strings":["Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7642-9044","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068181149","display_name":"Xiaofu Jin","orcid":"https://orcid.org/0000-0002-7239-3769"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Xiaofu Jin","raw_affiliation_strings":["Aalto University, Helsinki, Finland"],"raw_orcid":"https://orcid.org/0000-0002-7239-3769","affiliations":[{"raw_affiliation_string":"Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054048418","display_name":"Gaurav Jain","orcid":"https://orcid.org/0000-0002-9084-9395"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gaurav Jain","raw_affiliation_strings":["Columbia University, New York, New York, USA"],"raw_orcid":"https://orcid.org/0000-0002-9084-9395","affiliations":[{"raw_affiliation_string":"Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039483071","display_name":"W. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenshuo Zhang","raw_affiliation_strings":["Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0007-9226-0713","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230418","display_name":"Huamin Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Huamin Qu","raw_affiliation_strings":["Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3344-9694","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063454149","display_name":"Brian A. Smith","orcid":"https://orcid.org/0000-0003-2540-0839"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian A. Smith","raw_affiliation_strings":["Columbia University, New York, New York, USA"],"raw_orcid":"https://orcid.org/0000-0003-2540-0839","affiliations":[{"raw_affiliation_string":"Columbia University, New York, New York, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055104105","display_name":"Yukang Yan","orcid":"https://orcid.org/0000-0001-7515-3755"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yukang Yan","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, New York, USA"],"raw_orcid":"https://orcid.org/0000-0001-7515-3755","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, New York, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37849475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.37229999899864197,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.37229999899864197,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.260699987411499,"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":0.05869999900460243,"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/comprehension","display_name":"Comprehension","score":0.6133999824523926},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.475600004196167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/low-vision","display_name":"Low vision","score":0.35589998960494995},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.34630000591278076}],"concepts":[{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6133999824523926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5924000144004822},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.475600004196167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41519999504089355},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C2983447183","wikidata":"https://www.wikidata.org/wiki/Q737460","display_name":"Low vision","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3546000123023987},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33629998564720154},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3772363.3798425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3772363.3798425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-172042","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-172042","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W650442883","https://openalex.org/W1973976002","https://openalex.org/W2062865797","https://openalex.org/W2765653088","https://openalex.org/W2914307175","https://openalex.org/W2950504429","https://openalex.org/W3082679912","https://openalex.org/W3083532247","https://openalex.org/W3094385957","https://openalex.org/W3096780661","https://openalex.org/W3160237369","https://openalex.org/W3160767377","https://openalex.org/W3174854700","https://openalex.org/W3176493016","https://openalex.org/W3205898663","https://openalex.org/W3209713332","https://openalex.org/W4293112598","https://openalex.org/W4307475429","https://openalex.org/W4366548995","https://openalex.org/W4387793209","https://openalex.org/W4387793681","https://openalex.org/W4387793730","https://openalex.org/W4387801088","https://openalex.org/W4387801229","https://openalex.org/W4391940741","https://openalex.org/W4395443690","https://openalex.org/W4396832346","https://openalex.org/W4402521381","https://openalex.org/W4403333958","https://openalex.org/W4403576862","https://openalex.org/W4406880868","https://openalex.org/W4409767710","https://openalex.org/W4412035401","https://openalex.org/W4413146238","https://openalex.org/W4414711124","https://openalex.org/W4415444819","https://openalex.org/W7092208526"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"description":[1],"(AD)":[2],"makes":[3],"film":[4],"and":[5,10,75,109,125],"television":[6],"accessible":[7],"to":[8,35,45,70,98,105,113],"blind":[9],"low-vision":[11],"(BLV)":[12],"audiences":[13,69],"by":[14,88,120],"narrating":[15],"characters'":[16,47,73],"actions.":[17],"However,":[18],"in":[19],"scenes":[20],"with":[21,37,92],"lots":[22],"of":[23],"dialogue,":[24],"AD":[25],"often":[26],"omits":[27],"important":[28],"actions":[29,48,74],"because":[30],"it":[31],"is":[32,40],"constrained":[33],"not":[34,41],"overlap":[36],"speech.":[38],"It":[39],"yet":[42],"known":[43],"how":[44],"convey":[46,106],"during":[49],"dialogue.":[50],"We":[51,118],"present":[52],"Sonic":[53,81],"Stage,":[54],"a":[55,89],"system":[56],"that":[57],"automatically":[58],"transforms":[59],"dialogue":[60,97],"videos":[61],"into":[62],"an":[63],"interactive":[64,111,135],"spatial":[65,100],"soundscape,":[66],"enabling":[67],"BLV":[68,93],"intuitively":[71],"understand":[72],"movements":[76],"through":[77,132],"immersive":[78],"auditory":[79],"cues.":[80],"Stage":[82],"incorporates":[83],"three":[84],"core":[85],"techniques":[86],"informed":[87],"formative":[90],"study":[91],"viewers:":[94],"(1)":[95],"spatialized":[96],"represent":[99],"layout,":[101],"(2)":[102],"diegetic":[103],"sound":[104],"character":[107],"actions,":[108],"(3)":[110],"descriptions":[112],"provide":[114],"context-specific":[115],"visual":[116],"details.":[117],"conclude":[119],"outlining":[121],"our":[122],"evaluation":[123],"plan":[124],"highlighting":[126],"opportunities":[127],"for":[128],"enhancing":[129],"video":[130],"accessibility":[131],"more":[133],"immersive,":[134],"audio":[136],"representations.":[137]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-04-13T00:00:00"}