{"id":"https://openalex.org/W2132423630","doi":"https://doi.org/10.1109/icassp.2002.5743716","title":"Robust bi-modal speech recognition based on state synchronous modeling and stream weight optimization","display_name":"Robust bi-modal speech recognition based on state synchronous modeling and stream weight optimization","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2132423630","doi":"https://doi.org/10.1109/icassp.2002.5743716","mag":"2132423630"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743716","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratory","ATR Spoken Language Translation Research Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratory","institution_ids":[]},{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Japan","institution_ids":[]}]},{"author_position":"middle","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":false,"raw_author_name":"Ken'ichi Kumatani","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan","ATR Spoken Language Translation Research Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101808735","display_name":"Satoshi Tamura","orcid":"https://orcid.org/0000-0001-6916-4618"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Tamura","raw_affiliation_strings":["Tokyo Institute of Technology, Japan","ATR Spoken Language Translation Research Laboratories, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020994673"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3241,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.47372811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"309"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9983999729156494,"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":0.7940342426300049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.741543173789978},{"id":"https://openalex.org/keywords/synchronicity","display_name":"Synchronicity","score":0.598007321357727},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5669963359832764},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5616511106491089},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46581342816352844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45378658175468445},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4464259147644043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40156474709510803},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.09160825610160828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7940342426300049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.741543173789978},{"id":"https://openalex.org/C161394823","wikidata":"https://www.wikidata.org/wiki/Q1121101","display_name":"Synchronicity","level":2,"score":0.598007321357727},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5669963359832764},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5616511106491089},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46581342816352844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45378658175468445},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4464259147644043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40156474709510803},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.09160825610160828},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743716","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1516742535","https://openalex.org/W1591608209","https://openalex.org/W1829217008","https://openalex.org/W2102863932","https://openalex.org/W2124174353","https://openalex.org/W2142574745","https://openalex.org/W2228387523","https://openalex.org/W6635426702","https://openalex.org/W6681074423","https://openalex.org/W6689065797"],"related_works":["https://openalex.org/W560220919","https://openalex.org/W4253386791","https://openalex.org/W2493643238","https://openalex.org/W2772409069","https://openalex.org/W2495789417","https://openalex.org/W3167834828","https://openalex.org/W2347146170","https://openalex.org/W1527612580","https://openalex.org/W151416273","https://openalex.org/W2380535105"],"abstract_inverted_index":{"There":[0],"have":[1],"been":[2],"higher":[3,140],"demands":[4],"recently":[5],"for":[6,114,130],"Automatic":[7],"Speech":[8],"Recognition":[9],"(ASR)":[10],"systems":[11],"able":[12],"to":[13,25,143],"operate":[14],"robustly":[15],"in":[16,32,59],"acoustically":[17],"noisy":[18,115,131],"environments.":[19],"This":[20],"paper":[21],"proposes":[22],"a":[23,69,80,95,105,144],"method":[24,125,137],"effectively":[26],"integrate":[27],"audio":[28,47],"and":[29,48,56,64],"visual":[30,49],"information":[31,77],"audio-visual":[33,76],"(bi-modal)":[34],"ASR":[35],"systems.":[36],"Such":[37],"integration":[38],"inevitably":[39],"necessitates":[40],"modeling":[41,74],"of":[42,45,71,75,82],"the":[43,46,53,123,127,148],"synchronization":[44],"information.":[50],"To":[51],"address":[52],"time":[54],"lag":[55],"correlation":[57],"problems":[58],"individual":[60],"features":[61],"between":[62,99],"speech":[63,117],"lip":[65],"movements,":[66],"we":[67,102],"introduce":[68],"type":[70],"integrated":[72],"HMM":[73,83],"based":[78,110],"on":[79,111],"family":[81],"composition.":[84],"The":[85],"proposed":[86,124,136],"model":[87],"can":[88],"represent":[89],"state":[90],"synchronicity":[91,149],"not":[92],"only":[93],"within":[94],"phoneme":[96],"but":[97],"also":[98,103],"phonemes.":[100],"Furthermore,":[101],"propose":[104],"rapid":[106],"stream":[107],"weight":[108],"optimization":[109],"GPD":[112],"algorithm":[113],"bi-modal":[116],"recognition.":[118],"Evaluation":[119],"experiments":[120],"show":[121],"that":[122],"improves":[126],"recognition":[128],"accuracy":[129],"speech.":[132],"In":[133],"SNR=0dB":[134],"our":[135],"attained":[138],"16%":[139],"performance":[141],"compared":[142],"product":[145],"HMMs":[146],"without":[147],"re-estimation.":[150]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}