{"id":"https://openalex.org/W2102863932","doi":"https://doi.org/10.1109/icassp.1998.679695","title":"Discriminative training of HMM stream exponents for audio-visual speech recognition","display_name":"Discriminative training of HMM stream exponents for audio-visual speech recognition","publication_year":2002,"publication_date":"2002-11-27","ids":{"openalex":"https://openalex.org/W2102863932","doi":"https://doi.org/10.1109/icassp.1998.679695","mag":"2102863932"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1998.679695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"funder","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Potamianos","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110182290","display_name":"Hans Peter Graf","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"funder","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H.P. Graf","raw_affiliation_strings":["AT and T Research Laboratories, Red Bank, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Red Bank, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.076,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":109,"citation_normalized_percentile":{"value":0.967411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"3733","last_page":"3736"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998,"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":0.9998,"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":0.9913,"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":0.9894,"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/discriminative-model","display_name":"Discriminative model","score":0.8173946},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.65764964}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9085562},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8173946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.732022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7189009},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.65764964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5206108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47941634},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1998.679695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.77,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":12,"referenced_works":["https://openalex.org/W114677204","https://openalex.org/W1529401398","https://openalex.org/W1560013842","https://openalex.org/W177899316","https://openalex.org/W1829217008","https://openalex.org/W190875574","https://openalex.org/W1967878178","https://openalex.org/W2171244697","https://openalex.org/W4300104144","https://openalex.org/W4301155600","https://openalex.org/W72521054","https://openalex.org/W98035269"],"related_works":["https://openalex.org/W2940588515","https://openalex.org/W2404514746","https://openalex.org/W2167155152","https://openalex.org/W2160030256","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W1987783679","https://openalex.org/W1909151225","https://openalex.org/W1652783584","https://openalex.org/W1521297879"],"abstract_inverted_index":{"We":[0,71,99],"propose":[1],"the":[2,10,57,66,73,88,95,101,105,110],"use":[3],"of":[4,9,43,68,94,104],"discriminative":[5],"training":[6],"by":[7,46,55],"means":[8],"generalized":[11],"probabilistic":[12],"descent":[13],"(GPB)":[14],"algorithm":[15,75],"to":[16,35,87,109],"estimate":[17],"hidden":[18],"Markov":[19],"model":[20],"(HMM)":[21],"stream":[22,77],"exponents":[23,63],"for":[24,76],"audio-visual":[25,114],"speech":[26],"recognition.":[27],"Synchronized":[28],"audio":[29],"and":[30,39,61,84,113],"visual":[31],"features":[32],"are":[33],"used":[34],"respectively":[36],"train":[37],"audio-only":[38],"visual-only":[40],"single-stream":[41,59,115],"HMMs":[42,60],"identical":[44],"topology":[45],"maximum":[47],"likelihood.":[48],"A":[49],"two-stream":[50],"HMM":[51,108],"is":[52],"then":[53],"obtained":[54],"combining":[56],"two":[58],"introducing":[62],"that":[64],"weigh":[65],"log-likelihood":[67],"each":[69],"stream.":[70],"present":[72],"GPD":[74],"exponent":[78],"estimation,":[79],"consider":[80],"a":[81],"possible":[82],"initialization,":[83],"apply":[85],"it":[86],"single":[89],"speaker":[90],"connected":[91],"letters":[92],"task":[93],"AT&T":[96],"bimodal":[97],"database.":[98],"demonstrate":[100],"superior":[102],"performance":[103],"resulting":[106],"multi-stream":[107],"audio-only,":[111],"visual-only,":[112],"HMMs.":[116]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2102863932","counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2025-04-17T22:57:18.648928","created_date":"2016-06-24"}