{"id":"https://openalex.org/W16682072","doi":"https://doi.org/10.21437/icslp.2002-434","title":"DCT-based video features for audio-visual speech recognition","display_name":"DCT-based video features for audio-visual speech recognition","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W16682072","doi":"https://doi.org/10.21437/icslp.2002-434","mag":"16682072"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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/A5091747480","display_name":"Kristian Kroschel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristian Kroschel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107309845","display_name":"Christophe Savariaux","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Savariaux","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","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":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6295,"has_fulltext":false,"cited_by_count":58,"citation_normalized_percentile":{"value":0.95462602,"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":"1925","last_page":"1928"},"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":0.9998000264167786,"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":0.9973999857902527,"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":0.7695456743240356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.669434666633606},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.667328953742981},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6414309144020081},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45266470313072205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39932775497436523},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3038911521434784},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.2993253767490387},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.26010987162590027},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14546093344688416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695456743240356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.669434666633606},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.667328953742981},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6414309144020081},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45266470313072205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39932775497436523},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3038911521434784},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2993253767490387},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.26010987162590027},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14546093344688416}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/icslp.2002-434","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.301.228","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.301.228","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/ICSLP02.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.468.9141","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.468.9141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gipsa-lab.grenoble-inp.fr/~christophe.savariaux/PDF/ICSLP2002_martin.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W90026711","https://openalex.org/W204308143","https://openalex.org/W1492380776","https://openalex.org/W1529401398","https://openalex.org/W2036205336","https://openalex.org/W2100115174","https://openalex.org/W2106284211","https://openalex.org/W2119763131"],"related_works":["https://openalex.org/W2539140714","https://openalex.org/W2125883001","https://openalex.org/W2000099289","https://openalex.org/W2051360208","https://openalex.org/W1593153379","https://openalex.org/W3163107903","https://openalex.org/W3007022793","https://openalex.org/W1547145616","https://openalex.org/W4385822542","https://openalex.org/W1545198569"],"abstract_inverted_index":{"Encouraged":[0],"by":[1],"the":[2,6,16,19,23,52,55,58,62,107,110],"good":[3],"performance":[4,68],"of":[5,18,43,48,69,98,109],"DCT":[7,20,111],"in":[8,26,74],"audio-visual":[9,30,80,91,133],"speech":[10,31],"recognition":[11,24,32,38,113],"[1],":[12],"we":[13],"investigate":[14],"how":[15],"selec-tion":[17],"features":[21,123],"influences":[22],"scores":[25],"a":[27,35,41,75,131,146],"hybrid":[28],"ANN/HMM":[29],"sys-tem":[33],"on":[34,51],"continuous":[36],"word":[37],"task":[39],"with":[40,83,95],"vocab-ulary":[42],"30":[44],"numbers.":[45],"Three":[46],"sets":[47],"features,":[49],"based":[50,112],"mean":[53,63],"energy,":[54],"variance":[56,59],"and":[57,78],"relative":[60],"to":[61,86,116,127],"value,":[64],"were":[65],"chosen.":[66],"The":[67,90],"these":[70],"fea-tures":[71],"is":[72],"evaluated":[73],"video":[76],"only":[77],"an":[79],"recog-nition":[81],"scenario":[82],"varying":[84],"Signal":[85],"Noise":[87],"Ratios":[88],"(SNR).":[89],"tests":[92],"are":[93,114],"performed":[94],"5":[96],"types":[97],"addi-tional":[99],"noise":[100],"at":[101],"12":[102],"SNR":[103],"values":[104],"each.":[105],"Furthermore":[106],"results":[108],"compared":[115],"those":[117],"ob-tained":[118],"via":[119],"chroma-keyed":[120],"geometric":[121],"lip":[122],"[2].":[124],"In":[125],"order":[126],"achieve":[128],"this":[129],"comparison,":[130],"second":[132],"database":[134,141],"without":[135],"chroma-key":[136],"has":[137,142],"been":[138],"recorded.":[139],"This":[140],"similar":[143],"content":[144],"but":[145],"different":[147],"speaker.":[148],"1.":[149]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}