{"id":"https://openalex.org/W14943941","doi":"https://doi.org/10.21437/eurospeech.2001-293","title":"Comparing audio- and a-posteriori-probability-based stream confidence measures for audio-visual speech recognition","display_name":"Comparing audio- and a-posteriori-probability-based stream confidence measures for audio-visual speech recognition","publication_year":2001,"publication_date":"2001-09-03","ids":{"openalex":"https://openalex.org/W14943941","doi":"https://doi.org/10.21437/eurospeech.2001-293","mag":"14943941"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2001-293","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","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/A5071842389","display_name":"Martin Heckmann","orcid":"https://orcid.org/0000-0002-1794-1160"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin Heckmann","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035598278","display_name":"Thorsten Wild","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thorsten Wild","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187193","display_name":"Fr\u00e9d\u00e9ric Berthommier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Berthommier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091747480","display_name":"Kristian Kroschel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristian Kroschel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5668,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81714158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1023","last_page":"1026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9887999892234802,"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/speech-recognition","display_name":"Speech recognition","score":0.7569986581802368},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.697502076625824},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5131810307502747},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.49554312229156494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4881347119808197},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44648435711860657},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4460351765155792},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.42874160408973694},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.424015074968338},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.34704792499542236}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7569986581802368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697502076625824},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5131810307502747},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.49554312229156494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4881347119808197},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44648435711860657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4460351765155792},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.42874160408973694},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.424015074968338},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.34704792499542236},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.2001-293","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2001-293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th European Conference on Speech Communication and Technology (Eurospeech 2001)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.19.7279","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.19.7279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcs.shef.ac.uk/research/groups/spandh/projects/respite/publications/heckmann_eurospeech_01.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W90026711","https://openalex.org/W1500135552","https://openalex.org/W1520736967","https://openalex.org/W1529401398","https://openalex.org/W1869491686","https://openalex.org/W2036205336","https://openalex.org/W2119763131"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W1546240199","https://openalex.org/W2109142991","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674"],"abstract_inverted_index":{"During":[0],"the":[1,11,14,17,41,44,47,52,55,58,64,67,70,74,77,84,108,119,123,126,142],"fusion":[2,120],"of":[3,13,16,36,43,46,57,69,98,125],"audio":[4,20,59,109],"and":[5,51,66,94,122,132,141],"video":[6],"information":[7],"for":[8,115],"speech":[9],"recognition,":[10],"estimation":[12],"reliability":[15,37],"noise":[18,99,130],"affected":[19],"channel":[21],"is":[22,40,54],"crucial":[23],"to":[24,107],"get":[25],"meaningful":[26],"recognition":[27,90],"results.":[28],"In":[29],"this":[30],"paper":[31],"we":[32],"compare":[33],"two":[34],"types":[35,97,131],"measures.":[38],"One":[39],"use":[42],"statistics":[45],"phoneme":[48],"a-posteriori":[49],"probabilities":[50,71],"other":[53],"analysis":[56],"signal":[60],"itself.":[61],"We":[62],"implemented":[63],"entropy":[65],"dispersion":[68],"and,":[72],"from":[73],"audio-based":[75],"criteria,":[76],"so":[78],"called":[79],"Voicing":[80],"Index.":[81],"To":[82],"test":[83],"criteria":[85],"a":[86],"hybrid":[87],"ANN/HMM":[88],"audio-visual":[89],"system":[91],"was":[92,135],"used":[93],"5":[95],"different":[96],"at":[100],"12":[101],"SNR":[102,133],"levels":[103],"each":[104,116],"were":[105],"added":[106],"signal.":[110],"The":[111,137],"best":[112],"sigmoidal":[113],"fit":[114],"criterion":[117,127],"between":[118],"parameter":[121],"value":[124],"over":[128],"all":[129],"values":[134],"performed.":[136],"resulting":[138],"individual":[139],"errors":[140,146],"corresponding":[143],"averaged":[144],"relative":[145],"are":[147],"given.":[148]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}