{"id":"https://openalex.org/W4416016056","doi":"https://doi.org/10.1145/3746252.3761468","title":"<scp>VoiceVisSystem</scp> : End-to-End Voice-driven Data Visualization Generation from Natural Language Questions","display_name":"<scp>VoiceVisSystem</scp> : End-to-End Voice-driven Data Visualization Generation from Natural Language Questions","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416016056","doi":"https://doi.org/10.1145/3746252.3761468"},"language":null,"primary_location":{"id":"doi:10.1145/3746252.3761468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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/A5059498267","display_name":"Haodi Zhang","orcid":"https://orcid.org/0000-0001-8470-7246"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haodi Zhang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017600443","display_name":"Xiaohui Tang","orcid":"https://orcid.org/0009-0005-2550-7574"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Tang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047743457","display_name":"X.\u2010G. Zhang","orcid":"https://orcid.org/0009-0000-9385-2218"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhe Zhang","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102090006","display_name":"Jihua Zhou","orcid":"https://orcid.org/0009-0009-1787-4795"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jihua Zhou","raw_affiliation_strings":["Shenzhen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077688051","display_name":"Yuanfeng Song","orcid":"https://orcid.org/0000-0003-2221-9807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanfeng Song","raw_affiliation_strings":["WeBank Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"WeBank Co., Ltd, Shenzhen, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5059498267"],"corresponding_institution_ids":["https://openalex.org/I180726961"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35632148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6747","last_page":"6751"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.2379000037908554,"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/T10799","display_name":"Data Visualization and Analytics","score":0.2379000037908554,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1746000051498413,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.07689999788999557,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/visualization","display_name":"Visualization","score":0.6938999891281128},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5828999876976013},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5439000129699707},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.522599995136261},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5174999833106995},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.4616999924182892},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3190000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8507999777793884},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.6938999891281128},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.4616999924182892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38600000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3625999987125397},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.321399986743927},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.25290000438690186},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746252.3761468","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746252.3761468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 34th ACM International Conference on Information and Knowledge Management","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":10,"referenced_works":["https://openalex.org/W2425879071","https://openalex.org/W2611990000","https://openalex.org/W2945102109","https://openalex.org/W2991028016","https://openalex.org/W3125675327","https://openalex.org/W3174906424","https://openalex.org/W4226033575","https://openalex.org/W4281763536","https://openalex.org/W4281962965","https://openalex.org/W4290874921"],"related_works":[],"abstract_inverted_index":{"In":[0,19],"today's":[1],"digital":[2],"era,":[3],"data":[4,14,43],"visualization":[5],"(DV)":[6],"technology":[7],"has":[8],"become":[9],"indispensable":[10],"for":[11,34,76,151,160],"tasks":[12],"involving":[13],"processing":[15],"and":[16,82,95,107,114],"graphical":[17],"reasoning.":[18],"this":[20],"demonstration,":[21],"we":[22],"introduce":[23],"a":[24,45,121,132,148,157],"novel":[25],"automatic":[26],"DV":[27],"system":[28,63,135],"named":[29,71],"VoiceVisSystem.":[30],"VoiceVisSystem":[31,155],"is":[32,169],"designed":[33],"transforming":[35],"speech-form":[36],"natural":[37],"language":[38],"questions":[39],"(NLQs)":[40],"into":[41,117],"visual":[42],"representations,":[44],"task":[46],"formally":[47],"known":[48],"as":[49,78,112,128],"Speech-to-Vis.":[50],"Unlike":[51],"the":[52,58,74,85,92,96,100,104,108,125,129,137,152],"existing":[53],"cascaded":[54],"method":[55],"(e.g.,":[56],"Sevi),":[57],"core":[59],"component":[60],"of":[61,99,139],"our":[62,134],"relies":[64],"on":[65],"an":[66,79],"advanced":[67],"end-to-end":[68],"speech-to-vis":[69,153],"model":[70],"SpeechVisNet,":[72],"eliminating":[73],"need":[75],"text":[77,97],"intermediate":[80],"medium":[81],"directly":[83],"facilitating":[84],"conversion":[86],"from":[87],"Speech-form":[88],"to":[89],"DV.":[90],"Specifically,":[91],"speech":[93],"encoder":[94,98],"SpeechVisNet":[101],"respectively":[102],"take":[103],"user's":[105],"NLQs":[106],"corresponding":[109,126],"database":[110],"information":[111],"inputs":[113],"convert":[115],"them":[116],"hidden":[118],"representations.":[119],"Then,":[120],"grammar-based":[122],"decoder":[123],"generates":[124],"DVs":[127],"output.":[130],"As":[131],"result,":[133],"enjoys":[136],"benefits":[138],"avoiding":[140],"error":[141],"propagation,":[142],"thereby":[143],"enhancing":[144],"accuracy.":[145],"By":[146],"offering":[147],"seamless":[149],"solution":[150],"task,":[154],"presents":[156],"promising":[158],"tool":[159],"practical":[161],"applications":[162],"in":[163],"various":[164],"domains.":[165],"The":[166],"demonstration":[167],"video":[168],"available":[170],"at":[171],"https://1drv.ms/v/s!Ah2vhbolPBFMiSNPZLunJ6Qp6jqU?e=Shyq8R.":[172]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-08T00:00:00"}