{"id":"https://openalex.org/W1520736967","doi":"https://doi.org/10.21437/icslp.2000-643","title":"Stream confidence estimation for audio-visual speech recognition","display_name":"Stream confidence estimation for audio-visual speech recognition","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W1520736967","doi":"https://doi.org/10.21437/icslp.2000-643","mag":"1520736967"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-643","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","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/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5111579153","display_name":"C. Neti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chalapathy Neti","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024184433"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.5414,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95944088,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"vol. 3, 746","last_page":"749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9980000257492065,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7677001953125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.735724151134491},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6512918472290039},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4822181463241577},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.44499528408050537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43089228868484497},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4203995168209076},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40745311975479126},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37868189811706543},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3438032865524292},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14522069692611694},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06769922375679016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677001953125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.735724151134491},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6512918472290039},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4822181463241577},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.44499528408050537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43089228868484497},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4203995168209076},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40745311975479126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37868189811706543},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3438032865524292},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14522069692611694},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06769922375679016},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2000-643","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"6th International Conference on Spoken Language Processing (ICSLP 2000)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.22.6253","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.22.6253","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/ICSLP00_CONFIDENCE.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W147061571","https://openalex.org/W177899316","https://openalex.org/W190875574","https://openalex.org/W1523010034","https://openalex.org/W1529401398","https://openalex.org/W1546648362","https://openalex.org/W1560013842","https://openalex.org/W1664248204","https://openalex.org/W1922557984","https://openalex.org/W2015394094","https://openalex.org/W2051091181","https://openalex.org/W2102863932","https://openalex.org/W2157190406","https://openalex.org/W2170308399"],"related_works":["https://openalex.org/W2154415461","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W46679383","https://openalex.org/W2056066842","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"We":[0,24,62],"investigate":[1],"the":[2,29,49,73,86,101,104,156,172],"use":[3],"of":[4,12,32,38,72,171,179],"single":[5],"modality":[6],"confidence":[7,96,183],"measures":[8,97],"as":[9,67,124],"a":[10,39,90,130],"means":[11,37],"estimating":[13],"adaptive,":[14],"local":[15,78],"weights":[16],"for":[17],"improved":[18],"audio":[19,74,165],"-visual":[20],"automatic":[21],"speech":[22,137],"recognition.":[23],"limit":[25],"our":[26,127],"work":[27],"to":[28,58,163],"toy":[30],"problem":[31],"audio-visual":[33,121,138],"phonetic":[34,122,167],"classification":[35,152],"by":[36,84,126],"two-stream":[40],"Gaussian":[41],"mixture":[42],"model":[43],"(GMM),":[44],"where":[45],"each":[46],"stream":[47,65,77,95,102,112,144,160],"models":[48],"class":[50],"conditional":[51],"audio-":[52],"or":[53],"visual-only":[54],"observation":[55],"probability,":[56],"raised":[57],"an":[59,110,148,180],"appropriate":[60],"exponent.":[61],"consider":[63],"such":[64],"exponents":[66,161],"two-dimensional":[68],"piecewise":[69],"constant":[70],"functions":[71],"and":[75,80,109],"visual":[76],"confidences,":[79],"we":[81,146],"estimate":[82],"them":[83],"minimizing":[85],"misclassification":[87],"error":[88],"on":[89,129],"held-out":[91],"data":[92],"set.":[93],"Three":[94],"are":[98],"investigated,":[99],"namely":[100],"entropy,":[103],"n-best":[105,111],"likelihood":[106,113],"ratio":[107],"average,":[108],"dispersion":[114],"measure.":[115],"The":[116,169],"later":[117],"results":[118],"in":[119],"superior":[120],"classification,":[123],"indicated":[125],"experiments":[128],"260-subject,":[131],"40-hour":[132],"long,":[133],"large":[134],"vocabulary,":[135],"continuous":[136],"dataset.":[139],"By":[140],"using":[141],"local,":[142],"dispersion-based":[143],"exponents,":[145],"achieve":[147],"additional":[149],"20%":[150],"phone":[151],"accuracy":[153],"improvement":[154,157],"over":[155],"that":[158],"global":[159],"add":[162],"clean":[164],"-only":[166],"classification.":[168],"performance":[170],"algorithm":[173],"however":[174],"still":[175],"falls":[176],"significantly":[177],"short":[178],""oracle"":[181],"(cheating)":[182],"estimation":[184],"scheme.":[185]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}