{"id":"https://openalex.org/W1987446027","doi":"https://doi.org/10.1121/1.3654653","title":"Robust speech recognition with articulatory features using dynamic Bayesian networks","display_name":"Robust speech recognition with articulatory features using dynamic Bayesian networks","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W1987446027","doi":"https://doi.org/10.1121/1.3654653","mag":"1987446027"},"language":"en","primary_location":{"id":"doi:10.1121/1.3654653","doi":"https://doi.org/10.1121/1.3654653","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.3654653","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","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/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vikramjit Mitra","raw_affiliation_strings":["Speech Technol. and Res. Lab., SRI Int., 333 Ravenswood Ave., Menlo Park, CA 94025"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technol. and Res. Lab., SRI Int., 333 Ravenswood Ave., Menlo Park, CA 94025","institution_ids":["https://openalex.org/I1298353152"]}]},{"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 Labs., New Haven, CT 06511"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Haskins Labs., New Haven, CT 06511","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 Espy-Wilson","raw_affiliation_strings":["Univ. of Maryland, College Park, MD 20742"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Maryland, College Park, MD 20742","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elliot Saltzman","raw_affiliation_strings":["Boston Univ., Boston, MA 02115"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston Univ., Boston, MA 02115","institution_ids":["https://openalex.org/I111088046"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis Goldstein","raw_affiliation_strings":["Univ. of Southern California, Los Angeles, CA 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Southern California, Los Angeles, CA 90089","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"130","issue":"4_Supplement","first_page":"2408","last_page":"2408"},"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":0.0015999999595806003,"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":0.000699999975040555,"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/speech-recognition-in-noise","display_name":"speech recognition in noise","score":0.7609999775886536},{"id":"https://openalex.org/keywords/articulatory-features","display_name":"articulatory features","score":0.984000027179718},{"id":"https://openalex.org/keywords/dynamic-bayesian-networks","display_name":"dynamic Bayesian networks","score":0.9330000281333923},{"id":"https://openalex.org/keywords/articulatory-gestures","display_name":"articulatory gestures","score":0.8519999980926514},{"id":"https://openalex.org/keywords/mel-cepstral-features","display_name":"mel-cepstral features","score":0.8899999856948853},{"id":"https://openalex.org/keywords/word-recognition","display_name":"word recognition","score":0.7390000224113464},{"id":"https://openalex.org/keywords/phone-recognition","display_name":"phone recognition","score":0.9900000095367432},{"id":"https://openalex.org/keywords/acoustic-modeling","display_name":"acoustic modeling","score":0.6539999842643738},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7913119196891785},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7821921706199646},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5901828408241272},{"id":"https://openalex.org/C82142266","wikidata":"https://www.wikidata.org/wiki/Q3456604","display_name":"Dynamic Bayesian network","level":3,"score":0.5577083826065063},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5275570750236511},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4959803521633148},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46196526288986206},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46092909574508667},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.45823293924331665},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.43077394366264343},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4249423146247864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4232880771160126},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.42015576362609863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35047435760498047},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2321297824382782},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1121/1.3654653","doi":"https://doi.org/10.1121/1.3654653","is_oa":false,"landing_page_url":"https://doi.org/10.1121/1.3654653","pdf_url":null,"source":{"id":"https://openalex.org/S11296630","display_name":"The Journal of the Acoustical Society of America","issn_l":"0001-4966","issn":["0001-4966","1520-8524","1520-9024"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-b","erih-plus","jufo-3","ki-jl-1","medline","norway-2","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320226","host_organization_name":"Acoustical Society of America","host_organization_lineage":["https://openalex.org/P4310320226"],"host_organization_lineage_names":["Acoustical Society of America"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of the Acoustical Society of America","raw_type":"journal-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":0,"referenced_works":[],"related_works":["https://openalex.org/W7099720723","https://openalex.org/W2005741747","https://openalex.org/W2357391657","https://openalex.org/W2127846433","https://openalex.org/W2352540147","https://openalex.org/W7096692111","https://openalex.org/W2147284655","https://openalex.org/W1490506669","https://openalex.org/W7096134402","https://openalex.org/W2159596372"],"abstract_inverted_index":{"Previous":[0],"studies":[1],"have":[2,15],"proposed":[3],"ways":[4],"to":[5,26],"estimate":[6],"articulatory":[7,61,93,100,113],"information":[8,94,114],"from":[9,45],"the":[10,91,98,110,120],"acoustic":[11,78,81],"speech":[12],"signal":[13],"and":[14,49,67,97,123],"shown":[16],"that":[17,56,89,109],"when":[18],"used":[19],"with":[20,72],"standard":[21,73],"cepstral":[22,75],"features,":[23],"they":[24],"help":[25],"improve":[27],"word":[28,47,121],"recognition":[29,37,48,52,122,125],"performance":[30],"in":[31,54],"noise":[32,55,116],"for":[33,77,118],"a":[34,46,50,84],"connected":[35],"digit":[36],"task.":[38],"In":[39],"this":[40],"paper,":[41],"I":[42],"present":[43],"results":[44,107],"phone":[51,124],"experiments":[53],"uses":[57],"two":[58],"sets":[59],"of":[60,112],"representation:":[62],"continuous":[63,92],"(tract":[64],"variable":[65],"trajectories)":[66],"discrete":[68,99],"(articulatory":[69],"gestures)":[70],"along":[71],"mel":[74],"features":[76],"modeling.":[79],"The":[80],"model":[82],"is":[83],"dynamic":[85],"Bayesian":[86],"network":[87],"(DBN)":[88],"treats":[90],"as":[95,102],"observed":[96],"presentation":[101],"hidden":[103],"random":[104],"variables.":[105],"Our":[106],"indicate":[108],"use":[111],"improved":[115],"robustness":[117],"both":[119],"tasks":[126],"substantially.":[127]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}