{"id":"https://openalex.org/W2101818755","doi":"https://doi.org/10.1109/mmsp.2002.1203233","title":"Stream-weighted HMM for audio-visual ASR: a study on connected digit recognition","display_name":"Stream-weighted HMM for audio-visual ASR: a study on connected digit recognition","publication_year":2004,"publication_date":"2004-01-23","ids":{"openalex":"https://openalex.org/W2101818755","doi":"https://doi.org/10.1109/mmsp.2002.1203233","mag":"2101818755"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2002.1203233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE Workshop on Multimedia 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/A5023621766","display_name":"Michael Chan","orcid":"https://orcid.org/0000-0001-7417-7210"},"institutions":[{"id":"https://openalex.org/I57053284","display_name":"Rockwell Automation (United States)","ror":"https://ror.org/01sx1pm50","country_code":"US","type":"company","lineage":["https://openalex.org/I57053284"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M.T. Chan","raw_affiliation_strings":["Rockwell Scientific Company Limited Liability Company, Thousand Oaks, CA, USA","Rockwell Sci. Co., Thousand Oaks, CA, USA"],"affiliations":[{"raw_affiliation_string":"Rockwell Scientific Company Limited Liability Company, Thousand Oaks, CA, USA","institution_ids":["https://openalex.org/I57053284"]},{"raw_affiliation_string":"Rockwell Sci. Co., Thousand Oaks, CA, USA","institution_ids":["https://openalex.org/I57053284"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5023621766"],"corresponding_institution_ids":["https://openalex.org/I57053284"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17646424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"4"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9919999837875366,"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/computer-science","display_name":"Computer science","score":0.7553006410598755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7476868629455566},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.727350115776062},{"id":"https://openalex.org/keywords/digit-recognition","display_name":"Digit recognition","score":0.5453900098800659},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5240093469619751},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5094528794288635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.488300085067749},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4873414933681488},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.47833678126335144},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4382639229297638},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12305530905723572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10715988278388977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553006410598755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7476868629455566},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.727350115776062},{"id":"https://openalex.org/C2984784707","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Digit recognition","level":3,"score":0.5453900098800659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5240093469619751},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5094528794288635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.488300085067749},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4873414933681488},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.47833678126335144},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4382639229297638},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12305530905723572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10715988278388977},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2002.1203233","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2002.1203233","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2002 IEEE Workshop on Multimedia Signal Processing.","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":27,"referenced_works":["https://openalex.org/W1492120597","https://openalex.org/W1520736967","https://openalex.org/W1523010034","https://openalex.org/W1560013842","https://openalex.org/W1919971835","https://openalex.org/W1964178275","https://openalex.org/W1968813115","https://openalex.org/W2002591263","https://openalex.org/W2104095591","https://openalex.org/W2116418373","https://openalex.org/W2120974626","https://openalex.org/W2121430128","https://openalex.org/W2125013164","https://openalex.org/W2132217089","https://openalex.org/W2132290216","https://openalex.org/W2132423630","https://openalex.org/W2139790115","https://openalex.org/W2151043030","https://openalex.org/W2157190406","https://openalex.org/W3143122312","https://openalex.org/W3143966073","https://openalex.org/W3169507310","https://openalex.org/W6631099106","https://openalex.org/W6631338322","https://openalex.org/W6642413071","https://openalex.org/W6677158943","https://openalex.org/W6680143933"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2107304307","https://openalex.org/W2944691285","https://openalex.org/W1620730112","https://openalex.org/W2137566286"],"abstract_inverted_index":{"We":[0,16],"present":[1],"some":[2],"new":[3],"results":[4],"on":[5,75],"connected":[6],"digit":[7],"recognition":[8],"in":[9],"noisy":[10],"environments":[11],"by":[12],"audio-visual":[13],"speech":[14],"recognition.":[15],"derive":[17],"hybrid":[18],"(geometric-":[19],"and":[20,50],"appearance-based)":[21],"visual":[22,117],"lip":[23],"features":[24],"using":[25,47],"a":[26,35],"real-time":[27,120],"lip-tracking":[28],"algorithm":[29],"that":[30],"we":[31,43,59],"proposed":[32],"previously.":[33],"Using":[34],"single-speaker":[36],"corpus":[37],"modeled":[38],"after":[39],"the":[40,55,66,70,76,85,101,113,116],"TIDIGITS":[41],"database,":[42],"build":[44],"whole-word":[45],"HMMs":[46],"both":[48],"single-stream":[49],"2-stream":[51,56,81],"modeling":[52],"strategies.":[53],"For":[54],"HMM":[57,82],"method,":[58],"use":[60],"stream":[61],"dependent":[62],"weights":[63],"to":[64,100],"adjust":[65],"relative":[67],"contributions":[68],"of":[69,92,115],"two":[71],"feature":[72],"streams":[73],"based":[74],"acoustic":[77],"SNR":[78,97],"level.":[79],"The":[80],"consistently":[83],"gave":[84],"lowest":[86],"WER,":[87],"with":[88],"an":[89],"error":[90],"reduction":[91],"83%":[93],"at":[94,107],"-3":[95],"dB":[96],"level":[98],"compared":[99],"acoustic-only":[102],"baseline.":[103],"Visual-only":[104],"ASR":[105],"WER":[106],"6.85%":[108],"was":[109,123],"also":[110],"achieved,":[111],"showing":[112],"effectiveness":[114],"features.":[118],"A":[119],"system":[121],"prototype":[122],"developed":[124],"for":[125],"concept":[126],"demonstration.":[127]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}