{"id":"https://openalex.org/W2112348857","doi":"https://doi.org/10.1109/icme.2002.1035365","title":"Speaker independent audio-visual continuous speech recognition","display_name":"Speaker independent audio-visual continuous speech recognition","publication_year":2003,"publication_date":"2003-06-25","ids":{"openalex":"https://openalex.org/W2112348857","doi":"https://doi.org/10.1109/icme.2002.1035365","mag":"2112348857"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2002.1035365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"conference-paper","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/A5052554057","display_name":"Luhong Liang","orcid":"https://orcid.org/0009-0001-4190-006X"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luhong Liang","raw_affiliation_strings":["Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]},{"raw_affiliation_string":"Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783771","display_name":"Xiaoxing Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoxing Liu","raw_affiliation_strings":["Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]},{"raw_affiliation_string":"Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100845144","display_name":"Yibao Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yibao Zhao","raw_affiliation_strings":["Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]},{"raw_affiliation_string":"Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027964715","display_name":"Xiaobo Pi","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobo Pi","raw_affiliation_strings":["Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microcomputer Research Labs, Intel Corporation, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]},{"raw_affiliation_string":"Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113481101","display_name":"Ara Nefian","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210164234","display_name":"Microcom (United States)","ror":"https://ror.org/05npcf755","country_code":"US","type":"company","lineage":["https://openalex.org/I4210164234"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A.V. Nefian","raw_affiliation_strings":["Microcomputer Research Labs, Intel Corporation, Santa Clara, CA","Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microcomputer Research Labs, Intel Corporation, Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700","https://openalex.org/I4210164234"]},{"raw_affiliation_string":"Microcomput. Res. Lab., Intel Corp., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0399,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.97677319,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":null,"first_page":"25","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.986299991607666,"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"}},{"id":"https://openalex.org/T13579","display_name":"Image and Video Stabilization","score":0.9739999771118164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7779980897903442},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7698230743408203},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5410093665122986},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5398769378662109},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4422956109046936},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3732694685459137},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3709588050842285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3287501633167267},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3280695080757141},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.21919435262680054}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7779980897903442},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698230743408203},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5410093665122986},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5398769378662109},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4422956109046936},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3732694685459137},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3709588050842285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3287501633167267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3280695080757141},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.21919435262680054}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2002.1035365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2002.1035365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.954.8915","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.954.8915","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.anefian.com/research/nefian02_speaker.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W1560013842","https://openalex.org/W1576996184","https://openalex.org/W2083792893","https://openalex.org/W2099947851","https://openalex.org/W2121486117","https://openalex.org/W2129571380","https://openalex.org/W2156909104","https://openalex.org/W2164450870","https://openalex.org/W2164641162","https://openalex.org/W2166480741","https://openalex.org/W2171265988","https://openalex.org/W2217896605","https://openalex.org/W2799061466","https://openalex.org/W3099202502","https://openalex.org/W4230674625","https://openalex.org/W6683984541"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2122924390","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623","https://openalex.org/W2009814707"],"abstract_inverted_index":{"The":[0,27,59,103,124],"increase":[1],"in":[2,18,32],"the":[3,19,38,44,48,78,84,88,107,111,129,134,141,145],"number":[4],"of":[5,21,29,43,73,83,106,144,153],"multimedia":[6],"applications":[7],"that":[8,52,128],"require":[9],"robust":[10,71],"speech":[11,23,45,64,148],"recognition":[12,24,65,149],"systems":[13],"determined":[14],"a":[15,70,97],"large":[16],"interest":[17],"study":[20],"audio-visual":[22,62],"(AVSR)":[25],"systems.":[26],"use":[28],"visual":[30,41,74,89,114],"features":[31,51,75],"AVSR":[33],"is":[34],"justified":[35],"by":[36,138],"both":[37],"audio":[39,112,146],"and":[40,47,81,90,113],"modality":[42],"generation":[46],"need":[49],"for":[50],"are":[53,94],"invariant":[54],"to":[55],"acoustic":[56,91],"noise":[57],"perturbation.":[58],"speaker":[60],"independent":[61],"continuous":[63],"system":[66,131,150],"presented":[67],"relies":[68],"on":[69,133],"set":[72],"obtained":[76],"from":[77],"accurate":[79],"detection":[80],"tracking":[82],"mouth":[85],"region.":[86],"Further,":[87],"observation":[92],"sequences":[93],"integrated":[95],"using":[96],"coupled":[98],"hidden":[99],"Markov":[100],"(CHMM)":[101],"model.":[102],"statistical":[104],"properties":[105],"CHMM":[108],"can":[109],"model":[110],"state":[115],"asynchrony":[116],"while":[117],"preserving":[118],"their":[119],"natural":[120],"correlation":[121],"over":[122,139],"time.":[123],"experimental":[125],"results":[126],"show":[127],"current":[130],"tested":[132],"XM2VTS":[135],"database":[136],"reduces":[137],"55%":[140],"error":[142],"rate":[143],"only":[147],"at":[151],"SNR":[152],"0":[154],"dB.":[155]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
