{"id":"https://openalex.org/W7099346643","doi":null,"title":"Signal Level Fusion for Untethered Audio-Visual Interfaces","display_name":"Signal Level Fusion for Untethered Audio-Visual Interfaces","publication_year":2013,"publication_date":"2013-07-18","ids":{"openalex":"https://openalex.org/W7099346643"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.992","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.mit.edu/research/abstracts/abstracts2001/speech/03fisher.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5142873499","display_name":"John Sheridan Fisher","orcid":"https://orcid.org/0000-0003-4844-3495","observed_orcids":["https://orcid.org/0000-0003-4844-3495"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Fisher Iii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533","observed_orcids":["https://orcid.org/0000-0001-5453-8533"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.64758698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.989300012588501,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.989300012588501,"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/T12032","display_name":"Multisensory perception and integration","score":0.007799999788403511,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0006000000284984708,"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/cocktail-party-effect","display_name":"cocktail party effect","score":0.7009999752044678},{"id":"https://openalex.org/keywords/lip-movement","display_name":"lip movement","score":0.6570000052452087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.5509999990463257},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.7770000100135803},{"id":"https://openalex.org/keywords/subspace-projection","display_name":"subspace projection","score":0.7509999871253967},{"id":"https://openalex.org/keywords/human-machine-interaction","display_name":"human-machine interaction","score":0.6650000214576721},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"sensor fusion","score":0.43799999356269836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883000135421753},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6549000144004822},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6434000134468079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5866000056266785},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.5067999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805000126361847},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4503999948501587},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.41110000014305115},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.40880000591278076},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.31290000677108765},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.30550000071525574},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.992","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.mit.edu/research/abstracts/abstracts2001/speech/03fisher.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3139876855","https://openalex.org/W7099503650","https://openalex.org/W4242225362","https://openalex.org/W75825362","https://openalex.org/W2399526484","https://openalex.org/W2056961398","https://openalex.org/W1858125052","https://openalex.org/W4299573578","https://openalex.org/W7223081321","https://openalex.org/W2167709189"],"abstract_inverted_index":{"The":[0,66,78,109],"Problem:":[1],"In":[2,85],"a":[3,17],"crowded":[4],"and":[5,71,135,155],"noisy":[6],"room,":[7],"how":[8],"is":[9,68,83,112],"that":[10,46,73],"you":[11,47],"are":[12,51,57,62,64,138],"able":[13],"to":[14,38,43,69,92,113,140,147],"\u201chear":[15],"\u201d":[16],"conversation":[18],"without":[19,104],"getting":[20],"confused":[21],"by":[22],"interfering":[23],"sounds?":[24],"This":[25],"phenomenon,":[26],"commonly":[27],"called":[28],"the":[29,44,54,116,161],"\u201ccocktail":[30],"party":[31],"effect\u201d,":[32],"depends":[33],"somewhat":[34],"on":[35],"your":[36],"ability":[37],"relate":[39],"observed":[40,55],"lip":[41],"motion":[42],"sounds":[45,60],"hear.":[48],"Sounds":[49],"which":[50,61],"inconsistent":[52],"with":[53],"changes":[56],"ignored,":[58],"while":[59],"consistent":[63],"\u201cenhanced\u201d.":[65],"challenge":[67],"quantify":[70],"exploit":[72],"measure":[74],"of":[75,160],"consistency.":[76],"Motivation:":[77],"motivation":[79],"for":[80,97,119],"this":[81,148],"work":[82],"twofold.":[84],"our":[86],"focused":[87],"efforts":[88],"we":[89],"would":[90],"like":[91],"provide":[93],"untethered":[94],"audio-visual":[95],"input":[96],"human-computer":[98],"interface":[99],"applications":[100],"(e.g.":[101],"speech":[102],"recognition":[103],"attached":[105],"microphones":[106],"or":[107],"wires).":[108],"broader":[110],"goal":[111],"better":[114],"understand":[115],"learning":[117],"principles":[118],"multi-modal":[120],"fusion.":[121],"learned":[122],"subspace":[123],"f(V[i])":[124],"g(A[i])":[125],"Figure":[126],"1:":[127],"Basic":[128],"fusion":[129,166],"approach.":[130],"High-dimensional":[131],"frames":[132],"from":[133],"video":[134],"audio":[136],"sources":[137],"projected":[139],"informative":[141],"subspaces.":[142],"Previous":[143],"Work:":[144],"Existing":[145],"solutions":[146],"problem":[149],"generally":[150],"require":[151],"special":[152],"microphone":[153],"configurations,":[154],"often":[156],"assume":[157,169],"prior":[158],"knowledge":[159],"spurious":[162],"sources.":[163],"Classical":[164],"sensor":[165],"methods":[167],"typically":[168],"simple":[170]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2025-10-27T00:00:00"}
