{"id":"https://openalex.org/W2105768392","doi":"https://doi.org/10.1145/2556288.2556957","title":"Improving automatic speech recognition through head pose driven visual grounding","display_name":"Improving automatic speech recognition through head pose driven visual grounding","publication_year":2014,"publication_date":"2014-04-26","ids":{"openalex":"https://openalex.org/W2105768392","doi":"https://doi.org/10.1145/2556288.2556957","mag":"2105768392"},"language":"en","primary_location":{"id":"doi:10.1145/2556288.2556957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556288.2556957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGCHI 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/A5035399743","display_name":"Soroush Vosoughi","orcid":"https://orcid.org/0000-0002-2564-8909"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soroush Vosoughi","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA","Massachusetts Institute of Technology; ,; Cambridge MA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute of Technology; ,; Cambridge MA USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035399743"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3235","last_page":"3238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11707","display_name":"Gaze Tracking and Assistive Technology","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.850075900554657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919948220252991},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5457616448402405},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5270664691925049},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5114508867263794},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.47013789415359497},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.462558388710022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.850075900554657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919948220252991},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5457616448402405},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5270664691925049},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5114508867263794},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.47013789415359497},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.462558388710022},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2556288.2556957","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556288.2556957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGCHI Conference on Human Factors in Computing Systems","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":14,"referenced_works":["https://openalex.org/W943204654","https://openalex.org/W1796449931","https://openalex.org/W1974744233","https://openalex.org/W1985270055","https://openalex.org/W2022732461","https://openalex.org/W2052310875","https://openalex.org/W2056513832","https://openalex.org/W2086458350","https://openalex.org/W2111573508","https://openalex.org/W2129381838","https://openalex.org/W2137066512","https://openalex.org/W2156050092","https://openalex.org/W3210232381","https://openalex.org/W4296558785"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2077542787","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2081517010","https://openalex.org/W2121496884","https://openalex.org/W2387910809"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,17,54,76,114],"multimodal":[6],"speech":[7,130,134,160],"recognition":[8,135,161],"system":[9,21,58,71,118],"for":[10,78,158],"real":[11,102],"world":[12],"scene":[13,34,99],"description":[14,56],"tasks.":[15],"Given":[16,53],"visual":[18,33,36,80,126,166],"scene,":[19],"the":[20,29,32,39,51,57,61,68,79,83,95,98,129,147],"dynamically":[22],"biases":[23],"its":[24],"language":[25,64],"model":[26,65],"based":[27],"on":[28,47,121],"content":[30],"of":[31,38,82,141],"and":[35,100],"attention":[37,42,81],"speaker.":[40,84],"Visual":[41],"is":[43,107,165],"used":[44,92,157],"to":[45,66,93,155],"focus":[46],"likely":[48],"objects":[49,96],"within":[50],"scene.":[52],"spoken":[55],"then":[59],"uses":[60,72],"visually":[62],"biased":[63],"process":[67],"speech.":[69],"The":[70,117,137],"head":[73,104],"pose":[74,105],"as":[75,146],"proxy":[77],"Readily":[85],"available":[86],"standard":[87],"computer":[88],"vision":[89],"algorithms":[90],"are":[91],"recognize":[94],"in":[97],"automatic":[101],"time":[103],"estimation":[106],"done":[108],"using":[109],"depth":[110],"data":[111],"captured":[112],"via":[113],"Microsoft":[115],"Kinect.":[116],"was":[119],"evaluated":[120],"multiple":[122],"participants.":[123],"Overall,":[124],"incorporating":[125],"information":[127],"into":[128],"recognizer":[131],"greatly":[132],"improved":[133],"accuracy.":[136],"rapidly":[138],"decreasing":[139],"cost":[140],"3D":[142],"sensing":[143],"technologies":[144],"such":[145],"Kinect":[148],"allows":[149],"systems":[150],"with":[151],"similar":[152],"underlying":[153],"principles":[154],"be":[156],"many":[159],"tasks":[162],"where":[163],"there":[164],"information.":[167]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}