{"id":"https://openalex.org/W2135762233","doi":"https://doi.org/10.1109/icme.2005.1521429","title":"Rapid Feature Space Speaker Adaptation for Multi-Stream HMM-Based Audio-Visual Speech Recognition","display_name":"Rapid Feature Space Speaker Adaptation for Multi-Stream HMM-Based Audio-Visual Speech Recognition","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2135762233","doi":"https://doi.org/10.1109/icme.2005.1521429","mag":"2135762233"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018240777","display_name":"Jing Huang","orcid":"https://orcid.org/0000-0002-1370-7318"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010196081","display_name":"Etienne Marcheret","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Marcheret","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045869355","display_name":"Karthik Visweswariah","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Visweswariah","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.0214,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75913066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"338","last_page":"341"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976999759674072,"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":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8053711652755737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7701303362846375},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7585750818252563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5406925082206726},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5188849568367004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5088308453559875},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5061127543449402},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.49682238698005676},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4961925148963928},{"id":"https://openalex.org/keywords/headset","display_name":"Headset","score":0.4849863052368164},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4657287001609802},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4419926404953003},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42643868923187256},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3991276025772095},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3583822250366211}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8053711652755737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7701303362846375},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7585750818252563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406925082206726},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5188849568367004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5088308453559875},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5061127543449402},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.49682238698005676},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4961925148963928},{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.4849863052368164},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4657287001609802},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4419926404953003},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42643868923187256},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3991276025772095},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3583822250366211},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2005.1521429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.3623","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.3623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.ibm.com/AVSTG/ICME05.final.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W172154728","https://openalex.org/W196476531","https://openalex.org/W1492424399","https://openalex.org/W1523010034","https://openalex.org/W1974218343","https://openalex.org/W2002342963","https://openalex.org/W2074796660","https://openalex.org/W2076818396","https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2121551559","https://openalex.org/W2125027820","https://openalex.org/W2150473800","https://openalex.org/W2395273492","https://openalex.org/W3140749982","https://openalex.org/W4235272953","https://openalex.org/W6607016223","https://openalex.org/W6712039779"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Multi-stream":[0],"hidden":[1],"Markov":[2],"models":[3],"(HMMs)":[4],"have":[5],"recently":[6],"been":[7],"very":[8],"successful":[9],"in":[10],"audio-visual":[11,41,129],"speech":[12,42],"recognition,":[13],"where":[14],"the":[15,23,50,70,83,96,102,125,141,149,158,168],"audio":[16,84,151,160],"and":[17,61,106,153],"visual":[18,86],"streams":[19],"are":[20,122],"fused":[21],"at":[22],"final":[24],"decision":[25],"level.":[26],"In":[27,44],"this":[28],"paper":[29],"we":[30,46],"investigate":[31],"fast":[32,60,105],"feature":[33,66,112],"space":[34,67,113],"speaker":[35,72],"adaptation":[36,73,110],"using":[37,111],"multi-stream":[38,142,170],"HMMs":[39],"for":[40,64,133],"recognition.":[43],"particular,":[45],"focus":[47],"on":[48,124,148,157],"studying":[49],"performance":[51],"of":[52,75,104],"feature-space":[53],"maximum":[54,114],"likelihood":[55],"linear":[56,117],"regression":[57,118],"(fMLLR),":[58],"a":[59,92,115,134],"effective":[62],"method":[63],"estimating":[65],"transforms.":[68],"Unlike":[69],"common":[71],"techniques":[74],"MAP":[76],"or":[77,85],"MLLR,":[78],"fMLLR":[79,109,143],"does":[80],"not":[81],"change":[82],"HMM":[87],"parameters,":[88],"but":[89],"simply":[90],"applies":[91],"single":[93],"transform":[94],"to":[95,167],"testing":[97],"features.":[98],"We":[99],"also":[100],"address":[101],"problem":[103],"robust":[107],"on-line":[108],"posterior":[116],"(fMAPLR).":[119],"Adaptation":[120],"experiments":[121],"reported":[123],"IBM":[126],"infrared":[127],"headset":[128],"database.":[130],"On":[131],"average":[132],"20-speaker":[135],"1":[136],"hour":[137],"independent":[138],"test":[139],"set,":[140],"achieves":[144],"31%":[145],"relative":[146,155],"gain":[147,156],"clean":[150],"condition,":[152],"59%":[154],"noisy":[159],"condition":[161],"(approximately":[162],"7":[163],"dB)":[164],"as":[165],"compared":[166],"baseline":[169],"system":[171]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}