{"id":"https://openalex.org/W2147284655","doi":"https://doi.org/10.1109/icassp.2011.5947522","title":"Gesture-based Dynamic Bayesian Network for noise robust speech recognition","display_name":"Gesture-based Dynamic Bayesian Network for noise robust speech recognition","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2147284655","doi":"https://doi.org/10.1109/icassp.2011.5947522","mag":"2147284655"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947522","doi":"https://doi.org/10.1109/icassp.2011.5947522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947522","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"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/A5091201226","display_name":"Vikramjit Mitra","orcid":"https://orcid.org/0000-0002-2721-3976","observed_orcids":["https://orcid.org/0000-0002-2721-3976"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Institute of Systems Research & Department of ECE, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Systems Research & Department of ECE, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058543204","display_name":"Hosung Nam","orcid":"https://orcid.org/0000-0002-1523-346X","observed_orcids":["https://orcid.org/0000-0002-1523-346X"]},"institutions":[{"id":"https://openalex.org/I1319306116","display_name":"Haskins Laboratories","ror":"https://ror.org/003j5cv40","country_code":"US","type":"facility","lineage":["https://openalex.org/I1319306116"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hosung Nam","raw_affiliation_strings":["Haskins Laboratories, New Heaven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Haskins Laboratories, New Heaven, CT, USA","institution_ids":["https://openalex.org/I1319306116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078241735","display_name":"Carol Espy-Wilson","orcid":"https://orcid.org/0000-0002-1012-183X","observed_orcids":["https://orcid.org/0000-0002-1012-183X"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carol Y. Espy-Wilson","raw_affiliation_strings":["Institute of Systems Research & Department of ECE, University of Maryland, College Park, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Systems Research & Department of ECE, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009226999","display_name":"Elliot L. Saltzman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I1319306116","display_name":"Haskins Laboratories","ror":"https://ror.org/003j5cv40","country_code":"US","type":"facility","lineage":["https://openalex.org/I1319306116"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elliot Saltzman","raw_affiliation_strings":["Department of Physical Therapy and Athletic Training, Boston University, USA","Haskins Laboratories, New Heaven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physical Therapy and Athletic Training, Boston University, USA","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Haskins Laboratories, New Heaven, CT, USA","institution_ids":["https://openalex.org/I1319306116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110122617","display_name":"Louis M. Goldstein","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I1319306116","display_name":"Haskins Laboratories","ror":"https://ror.org/003j5cv40","country_code":"US","type":"facility","lineage":["https://openalex.org/I1319306116"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis Goldstein","raw_affiliation_strings":["Department of Linguistics, University of Southern California, USA","Haskins Laboratories, New Heaven, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Haskins Laboratories, New Heaven, CT, USA","institution_ids":["https://openalex.org/I1319306116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0022,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88121417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5172","last_page":"5175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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/T10860","display_name":"Speech and Audio Processing","score":0.002400000113993883,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamic-bayesian-networks","display_name":"dynamic Bayesian networks","score":0.8019999861717224},{"id":"https://openalex.org/keywords/noise-robust-speech-recognition","display_name":"noise-robust speech recognition","score":0.8100000023841858},{"id":"https://openalex.org/keywords/articulatory-gestures","display_name":"articulatory gestures","score":0.9330000281333923},{"id":"https://openalex.org/keywords/vocal-tract-constriction","display_name":"vocal tract constriction","score":0.8169999718666077},{"id":"https://openalex.org/keywords/hidden-variables","display_name":"hidden variables","score":0.7770000100135803},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.6150000095367432},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.5249999761581421},{"id":"https://openalex.org/keywords/aurora-2","display_name":"Aurora 2","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8658215999603271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8140783309936523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7922389507293701},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.6699407696723938},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.618387758731842},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.5798449516296387},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5252577662467957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188068747520447},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.489275187253952},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.44972115755081177},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44249606132507324},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4213216304779053},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4020541310310364},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3272295594215393},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.30845382809638977},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947522","doi":"https://doi.org/10.1109/icassp.2011.5947522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947522","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W62553166","https://openalex.org/W117449184","https://openalex.org/W1490506669","https://openalex.org/W1509905243","https://openalex.org/W1541680420","https://openalex.org/W1608231129","https://openalex.org/W1986174057","https://openalex.org/W2003890417","https://openalex.org/W2043199434","https://openalex.org/W2068447135","https://openalex.org/W2111492050","https://openalex.org/W2131770202","https://openalex.org/W2151484683","https://openalex.org/W2154074091","https://openalex.org/W2991401689"],"related_works":["https://openalex.org/W2005741747","https://openalex.org/W1987446027","https://openalex.org/W1974379374","https://openalex.org/W175821084","https://openalex.org/W7099720723","https://openalex.org/W117449184","https://openalex.org/W2134295038","https://openalex.org/W20350175","https://openalex.org/W2017210410","https://openalex.org/W2106144006"],"abstract_inverted_index":{"Previously":[0],"we":[1,50,92],"have":[2,20],"proposed":[3,90],"different":[4],"models":[5,29],"for":[6,54,84,98],"estimating":[7,55],"articulatory":[8],"gestures":[9,77],"and":[10,61],"vocal":[11,74],"tract":[12,75],"variable":[13],"(TV)":[14],"trajectories":[15],"from":[16],"synthetic":[17],"speech.":[18],"We":[19,133],"shown":[21],"that":[22,72],"when":[23],"deployed":[24],"on":[25,58],"natural":[26,59],"speech,":[27],"such":[28],"can":[30],"help":[31],"to":[32],"improve":[33],"the":[34,82,89,99,111,124],"noise":[35],"robustness":[36],"of":[37,102],"a":[38,52,63,94,118],"hidden":[39,79,115],"Markov":[40],"model":[41,53],"(HMM)":[42],"based":[43,68,128],"speech":[44,60,69],"recognition":[45,70,96],"system.":[46],"In":[47],"this":[48],"paper":[49],"propose":[51],"TVs":[56],"trained":[57],"present":[62],"Dynamic":[64],"Bayesian":[65],"Network":[66],"(DBN)":[67],"architecture":[71,91,120],"treats":[73],"constriction":[76],"as":[78,114],"variables,":[80],"eliminating":[81],"necessity":[83],"explicit":[85],"gesture":[86],"recognition.":[87],"Using":[88],"performed":[93],"word":[95],"task":[97],"noisy":[100],"data":[101],"Aurora":[103],"2.":[104],"Significant":[105],"improvement":[106],"was":[107],"observed":[108],"in":[109,117],"using":[110,122],"gestural":[112],"information":[113],"variables":[116],"DBN":[119,131],"over":[121],"only":[123],"mel-frequency":[125],"cepstral":[126],"coefficient":[127],"HMM":[129],"or":[130],"backend.":[132],"also":[134],"compare":[135],"our":[136],"results":[137],"with":[138],"other":[139],"noise-robust":[140],"front":[141],"ends.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}