{"id":"https://openalex.org/W2134764753","doi":"https://doi.org/10.1109/icme.2001.1237846","title":"An adaptive integration based on product hmm for audio-visual speech recognition","display_name":"An adaptive integration based on product hmm for audio-visual speech recognition","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2134764753","doi":"https://doi.org/10.1109/icme.2001.1237846","mag":"2134764753"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2001.1237846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 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/A5053915317","display_name":"Kenichi Kumatani","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"K. Kumatani","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","Nara Institute of Science and Technology, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080776631","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0003-3492-7093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Nakamura","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Soraku-gun, Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021868389","display_name":"Kiyohiro Shikano","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Shikano","raw_affiliation_strings":["Nara Institute of Science and Technology, Nara, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Nara, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053915317"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.9094,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.76649628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"813","last_page":"816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8125936985015869},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7568398118019104},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6717216968536377},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4916992783546448},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.46671172976493835},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4280398488044739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4260466396808624},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.41498544812202454},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40599116683006287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4014107584953308},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.39150455594062805}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125936985015869},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7568398118019104},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6717216968536377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4916992783546448},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.46671172976493835},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4280398488044739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4260466396808624},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.41498544812202454},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40599116683006287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4014107584953308},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.39150455594062805},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2001.1237846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Multimedia and Expo, 2001. ICME 2001.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W11855449","https://openalex.org/W1516742535","https://openalex.org/W1591608209","https://openalex.org/W1967878178","https://openalex.org/W2003333103","https://openalex.org/W2102863932","https://openalex.org/W2124174353","https://openalex.org/W3148186152","https://openalex.org/W6600454051","https://openalex.org/W6631209828","https://openalex.org/W6635426702","https://openalex.org/W6675533774","https://openalex.org/W6793064978"],"related_works":["https://openalex.org/W2121652828","https://openalex.org/W2157598242","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W2620660273","https://openalex.org/W4243125559","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"higher":[3],"demands":[4],"recently":[5],"for":[6,120],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR)":[10],"systems":[11],"able":[12],"to":[13,25],"operate":[14],"robustly":[15],"in":[16,32,61],"acoustically":[17],"noisy":[18,121],"environments.":[19],"This":[20],"paper":[21],"proposes":[22],"a":[23,59],"method":[24,91,115],"effectively":[26],"integrate":[27],"audio":[28,50],"and":[29,51,54,72,79],"visual":[30,52],"information":[31],"audiovisual":[33],"(bi-modal)":[34],"ASR":[35],"systems.":[36],"For":[37],"such":[38],"integration,":[39],"the":[40,49,66,70,76,81,100,106,113,117],"following":[41],"issues":[42],"are":[43],"important:":[44],"(1)":[45],"The":[46,56],"synchronization":[47],"of":[48,58,69],"information,":[53],"(2)":[55],"optimization":[57],"system":[60],"its":[62],"environment.":[63],"In":[64,95],"(1),":[65],"individual":[67],"feature":[68],"speech":[71],"lip":[73],"movements":[74],"has":[75,80],"time":[77],"lag,":[78],"correlation.":[82],"To":[83],"address":[84],"this":[85],"problem,":[86],"we":[87,97],"introduce":[88],"an":[89],"integration":[90],"using":[92],"HMM":[93],"composition.":[94],"(2),":[96],"examine":[98],"whether":[99],"GPD":[101],"algorithm":[102],"can":[103],"adaptively":[104],"estimate":[105],"stream":[107],"weights.":[108],"Evaluation":[109],"experiments":[110],"show":[111],"that":[112],"proposed":[114],"improves":[116],"recognition":[118],"accuracy":[119],"speech.":[122]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}