{"id":"https://openalex.org/W2108101067","doi":"https://doi.org/10.1109/icassp.2004.1326121","title":"A stream-weight optimization method for audio-visual speech recognition using multi-stream HMMs","display_name":"A stream-weight optimization method for audio-visual speech recognition using multi-stream HMMs","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2108101067","doi":"https://doi.org/10.1109/icassp.2004.1326121","mag":"2108101067"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100501600/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059977188","display_name":"Shinichi Tamura","orcid":"https://orcid.org/0000-0003-2335-3557"},"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":"S. Tamura","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084374665","display_name":"Koji Iwano","orcid":"https://orcid.org/0000-0002-7373-5353"},"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":"K. Iwano","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009532108","display_name":"Sadaoki Furui","orcid":null},"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":"S. Furui","raw_affiliation_strings":["Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","Department of Computer Science, Tokyo Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Meguro, Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Department of Computer Science, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":2.2913,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.88550816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.998199999332428,"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":0.7795733213424683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7519076466560364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48399877548217773},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4597516357898712},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4365408718585968},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3642142415046692},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.09075111150741577}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795733213424683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7519076466560364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48399877548217773},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4597516357898712},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4365408718585968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3642142415046692},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.09075111150741577}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2004.1326121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00107062","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100501600","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100501600/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:00107595","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100502163","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:t2r2.star.titech.ac.jp:00107062","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100501600","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100501600/ATD100000413/","source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2108101067.pdf","grobid_xml":"https://content.openalex.org/works/W2108101067.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W11855449","https://openalex.org/W98035269","https://openalex.org/W1516742535","https://openalex.org/W1571194703","https://openalex.org/W2146871184","https://openalex.org/W2220874846","https://openalex.org/W6600454051","https://openalex.org/W6604012948","https://openalex.org/W6631209828","https://openalex.org/W6634211021","https://openalex.org/W6688670458"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"For":[0],"multi-stream":[1,64],"HMM":[2,65],"that":[3],"are":[4,42,57,74],"widely":[5],"used":[6],"in":[7,82],"audio-visual":[8,61],"speech":[9,37,80],"recognition,":[10],"it":[11],"is":[12,66],"important":[13],"to":[14],"automatically":[15],"and":[16,44,54,70,93,104],"properly":[17],"adjust":[18],"stream":[19],"weights.":[20],"This":[21],"paper":[22],"proposes":[23],"a":[24,30,99,105],"stream-weight":[25],"optimization":[26,95],"technique":[27],"based":[28],"on":[29],"likelihood-ratio":[31],"maximization":[32],"criterion.":[33],"In":[34],"our":[35,94],"audiovisual":[36],"recognition":[38],"system,":[39],"video":[40],"signals":[41],"captured":[43],"converted":[45],"into":[46,59],"visual":[47,55,71],"features":[48,56],"using":[49,76],"HMM-based":[50],"techniques.":[51],"Extracted":[52],"acoustic":[53],"concatenated":[58],"an":[60],"vector.":[62],"A":[63],"obtained":[67],"from":[68],"audio":[69],"HMM.":[72],"Experiments":[73],"conducted":[75],"Japanese":[77],"connected":[78],"digit":[79],"recorded":[81],"real-world":[83],"environments.":[84],"Applying":[85],"the":[86,113],"MLLR":[87],"(maximum":[88],"likelihood":[89],"linear":[90],"regression)":[91],"adaptation":[92],"method,":[96],"we":[97],"achieve":[98],"29%":[100],"absolute":[101],"accuracy":[102],"improvement":[103],"76%":[106],"relative":[107],"error":[108],"rate":[109],"reduction":[110],"compared":[111],"with":[112],"audio-only":[114],"scheme.":[115]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}