{"id":"https://openalex.org/W90026711","doi":"https://doi.org/10.21437/icslp.2000-739","title":"Labeling audio-visual speech corpora and training an ANN/HMM audio-visual speech recognition system","display_name":"Labeling audio-visual speech corpora and training an ANN/HMM audio-visual speech recognition system","publication_year":2000,"publication_date":"2000-10-16","ids":{"openalex":"https://openalex.org/W90026711","doi":"https://doi.org/10.21437/icslp.2000-739","mag":"90026711"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2000-739","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-739","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/A5071842389","display_name":"Martin Heckmann","orcid":"https://orcid.org/0000-0002-1794-1160"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Heckmann","raw_affiliation_strings":["Karlsruhe Institute of technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of technology","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108187193","display_name":"Fr\u00e9d\u00e9ric Berthommier","orcid":null},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9ric Berthommier","raw_affiliation_strings":["[Grenoble Institute of Technology]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Grenoble Institute of Technology]","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047238259","display_name":"Christophe Savario","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Savario","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091747480","display_name":"Kristian Kroschel","orcid":null},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kristian Kroschel","raw_affiliation_strings":["[Grenoble Institute of Technology]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Grenoble Institute of Technology]","institution_ids":["https://openalex.org/I106785703"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6345,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83314233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"vol. 4, 9","last_page":"12"},"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9980999827384949,"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/speech-recognition","display_name":"Speech recognition","score":0.8258848190307617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7804427742958069},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7631129622459412},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6626595854759216},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6511180996894836},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4853345453739166},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.42777788639068604},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.39016491174697876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3853706121444702},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.29414093494415283},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18774530291557312}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8258848190307617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7804427742958069},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7631129622459412},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6626595854759216},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6511180996894836},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4853345453739166},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.42777788639068604},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.39016491174697876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3853706121444702},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29414093494415283},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18774530291557312}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.2000-739","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2000-739","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:10.1.1.301.7627","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.7627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://home.arcor.de/martin.heckmann/Publications/2000-2003/ICSLP2000.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.33.3053","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.33.3053","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_icslp_00.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2014621385","https://openalex.org/W2036205336","https://openalex.org/W2100643000","https://openalex.org/W2118977726","https://openalex.org/W2137644731"],"related_works":["https://openalex.org/W90026711","https://openalex.org/W2055487029","https://openalex.org/W3089379469","https://openalex.org/W1987021544","https://openalex.org/W1587401114","https://openalex.org/W2403424637","https://openalex.org/W3166169565","https://openalex.org/W2122924390","https://openalex.org/W62067635","https://openalex.org/W1502340135"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,12,20,36,64,73,145],"method":[3],"to":[4,10,71,84,103,125,131,141],"label":[5,85],"an":[6,77],"audio-visual":[7,15,91,152],"database":[8,39,50,58,106,148],"and":[9,107],"setup":[11],"system":[13,154],"for":[14],"speech":[16],"recognition":[17,153],"based":[18],"on":[19,35],"hybrid":[21],"Artificial":[22],"Neural":[23],"Network/Hidden":[24],"Markov":[25],"Model":[26],"(ANN/HMM)":[27],"approach.":[28],"The":[29,49],"multi-stage":[30],"labeling":[31,62,95,114,118,137],"process":[32],"is":[33,69,96,119],"presented":[34],"new":[37,105],"audiovisual":[38],"recorded":[40],"at":[41,122],"the":[42,56,61,86,90,101,104,109,112,116,133,136,150],"Institute":[43],"de":[44],"la":[45],"Communication":[46],"Parl\u00e9e":[47],"(ICP).":[48],"was":[51],"generated":[52],"via":[53,99],"transposition":[54],"of":[55,67,76,89,135],"audio":[57,87,113,147],"NUMBERS95.":[59],"For":[60],"first":[63],"large":[65,146],"subset":[66],"NUMBERS95":[68],"used":[70],"achieve":[72],"bootstrap":[74],"training":[75],"ANN,":[78],"which":[79],"can":[80],"then":[81,115],"be":[82],"employed":[83],"part":[88],"database.":[92],"This":[93],"initial":[94],"further":[97],"improved":[98],"readapting":[100],"ANN":[102],"reperforming":[108],"labeling.":[110],"From":[111],"video":[117],"derived.":[120],"Tests":[121],"different":[123],"Signal":[124],"Noise":[126],"Ratios":[127],"(SNR)":[128],"are":[129],"performed":[130],"demonstrate":[132],"efficiency":[134],"process.":[138],"Furthermore":[139],"ways":[140],"incorporate":[142],"information":[143],"from":[144],"into":[149],"final":[151],"were":[155],"investigated.":[156],"1":[157]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}