{"id":"https://openalex.org/W98035269","doi":null,"title":"Speaker independent audio-visual database for bimodal ASR.","display_name":"Speaker independent audio-visual database for bimodal ASR.","publication_year":1997,"publication_date":"1997-01-01","ids":{"openalex":"https://openalex.org/W98035269","mag":"98035269"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.8686","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.8686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/AVSTG/AVSP97_DATABASE.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/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124","observed_orcids":["https://orcid.org/0000-0002-9833-7124"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-9833-7124","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012049132","display_name":"Eric Cosatto","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eric Cosatto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110182290","display_name":"Hans Peter Graf","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hans Peter Graf","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048848214","display_name":"David B. Roe","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David B. Roe","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":3.9826,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.92884787,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9726999998092651,"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":0.9726999998092651,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.019600000232458115,"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"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.0017000000225380063,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual-speech-recognition","display_name":"audio-visual speech recognition","score":0.9390000104904175},{"id":"https://openalex.org/keywords/speaker-independent-speech-recognition","display_name":"speaker-independent recognition","score":0.8080000281333923},{"id":"https://openalex.org/keywords/visual-speech","display_name":"visual speech","score":0.4269999861717224},{"id":"https://openalex.org/keywords/lip-contour-extraction","display_name":"lip contour extraction","score":0.8259999752044678},{"id":"https://openalex.org/keywords/lip-reading","display_name":"lip reading","score":0.6769999861717224},{"id":"https://openalex.org/keywords/connected-digits","display_name":"connected digits","score":0.8539999723434448},{"id":"https://openalex.org/keywords/confusable-words","display_name":"confusable words","score":0.7129999995231628}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6609117984771729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6067567467689514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5433729887008667},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38328394293785095},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3333872854709625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3219061493873596},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18750405311584473}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.8686","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.8686","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/AVSTG/AVSP97_DATABASE.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.49.8494","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.8494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/~makis/paper_AVSP_97.ps","raw_type":"text"},{"id":"mag:98035269","doi":null,"is_oa":false,"landing_page_url":"http://www.isca-speech.org/archive_open/avsp97/av97_065.html","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"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/W171560785","https://openalex.org/W2539140714","https://openalex.org/W7160297052","https://openalex.org/W7097841143","https://openalex.org/W5769393","https://openalex.org/W2497106782","https://openalex.org/W2129122669","https://openalex.org/W1921959515","https://openalex.org/W124776053","https://openalex.org/W2366864536"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,11,35,73,126],"audio-visual":[4,45,121],"database":[5,20,55],"collected":[6,57],"at":[7],"AT&T":[8],"Labs#Research":[9],"for":[10,85],"study":[12,36],"of":[13,22,37,64,79],"bimodal":[14],"speech":[15,103,122],"recognition.":[16],"To":[17],"date,":[18],"this":[19,112],"consists":[21],"twomultiple":[23],"speaker":[24,43,52,82,128],"parts,":[25],"namely":[26],"isolated":[27],"confusable":[28],"words":[29],"and":[30,40,62,81,88,114,120],"connected":[31,53,129],"letters,":[32],"thus":[33,93],"allowing":[34],"some":[38],"popular":[39],"relatively":[41],"simple":[42],"independent":[44,83],"recognition":[46,123],"tasks.":[47],"In":[48],"addition,":[49],"a":[50],"single":[51,127],"digits":[54,130],"is":[56,92],"to":[58,97,111],"facilitate":[59],"speedy":[60],"development":[61],"testing":[63],"various":[65],"algorithms.":[66],"Intentionally,no":[67],"lip":[68,89],"markings":[69],"are":[70],"used":[71],"on":[72,125],"subjects":[74],"during":[75],"data":[76],"collection.":[77],"Development":[78],"robust":[80],"algorithms":[84],"mouth":[86],"location":[87],"contour":[90],"extraction":[91],"necessary":[94],"in":[95],"order":[96],"obtain":[98],"informative":[99],"features":[100],"about":[101],"visual":[102],"#visual":[104],"front":[105],"end#.":[106],"We":[107],"describe":[108],"our":[109,117],"approach":[110],"problem,":[113],"we":[115],"report":[116],"automatic":[118],"speech-reading":[119],"results":[124],"task.":[131],"1.":[132]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}
