{"id":"https://openalex.org/W2124455255","doi":"https://doi.org/10.1109/icme.2001.1237674","title":"HMM modeling for audio-visual speech recognition","display_name":"HMM modeling for audio-visual speech recognition","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2124455255","doi":"https://doi.org/10.1109/icme.2001.1237674","mag":"2124455255"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2001.1237674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237674","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/A5087842192","display_name":"Zhi Qi","orcid":"https://orcid.org/0000-0003-4699-6440"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Qi Zhi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047635730","display_name":"M.N. Kaynak","orcid":"https://orcid.org/0000-0002-5358-9408"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"M.N. Kaynak","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111890923","display_name":"K. Sengupta","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"K. Sengupta","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013649214","display_name":"Adrian David Cheok","orcid":"https://orcid.org/0000-0001-6316-2339"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"A.D. Cheok","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102723221","display_name":"C.C. Ko","orcid":"https://orcid.org/0000-0003-1950-6979"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"C.C. Ko","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National University of Singapore, Singapore","National University of Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087842192"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.61895911,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"139"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9979000091552734,"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":0.994700014591217,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8595162034034729},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8338137269020081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808753848075867},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4842061996459961},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46518296003341675},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42678603529930115},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4117988348007202},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4102781116962433}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8595162034034729},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8338137269020081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808753848075867},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4842061996459961},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46518296003341675},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42678603529930115},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4117988348007202},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4102781116962433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2001.1237674","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2001.1237674","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W22517275","https://openalex.org/W1560013842","https://openalex.org/W1929733467","https://openalex.org/W2015394094","https://openalex.org/W2121486117","https://openalex.org/W2124174353","https://openalex.org/W2137317849","https://openalex.org/W6633431331"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W2640905660","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Bimodal":[0],"speech":[1,9,40,57,114],"recognition":[2,115,122],"is":[3,84],"a":[4,14,43,62,118],"robust":[5],"technique":[6],"for":[7],"automated":[8],"analysis,":[10],"and":[11,59,92],"has":[12,66,117],"received":[13],"lot":[15],"of":[16,30,37,46,76,80,89,104,127],"attention":[17],"in":[18,55,125],"the":[19,28,31,35,38,47,77,85,90,93,100,112],"last":[20],"few":[21],"decades.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26],"analyze":[27],"effect":[29],"HMM":[32,49,82],"models":[33,50],"on":[34],"performance":[36],"bimodal":[39,56,113],"recognizer,":[41],"present":[42],"comparative":[44],"analysis":[45],"different":[48,101],"that":[51,96],"can":[52],"be":[53],"used":[54],"recognition,":[58],"finally":[60],"propose":[61],"novel":[63,86],"model,":[64],"which":[65],"been":[67],"experimentally":[68],"verified":[69],"to":[70,109],"perform":[71],"better":[72],"than":[73],"others.":[74],"One":[75],"unique":[78],"characteristic":[79],"our":[81],"model":[83],"fusion":[87],"strategy":[88],"acoustic":[91],"visual":[94],"features,":[95],"takes":[97],"into":[98],"account":[99],"sampling":[102],"rates":[103],"these":[105],"two":[106],"signals.":[107],"Compared":[108],"audio":[110],"only,":[111],"scheme":[116],"much":[119],"more":[120],"improved":[121],"accuracy,":[123],"especially":[124],"presence":[126],"noise.":[128]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}