{"id":"https://openalex.org/W2137919539","doi":"https://doi.org/10.1109/tasl.2009.2023162","title":"Enhanced Phone Posteriors for Improving Speech Recognition Systems","display_name":"Enhanced Phone Posteriors for Improving Speech Recognition Systems","publication_year":2009,"publication_date":"2009-06-16","ids":{"openalex":"https://openalex.org/W2137919539","doi":"https://doi.org/10.1109/tasl.2009.2023162","mag":"2137919539"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2023162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2023162","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146047","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047412162","display_name":"Hamed Ketabdar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093367","display_name":"Deutsche Telekom (Germany)","ror":"https://ror.org/00m8prc86","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093367"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hamed Ketabdar","raw_affiliation_strings":["Deutsche Telekom Research and Development Laboratories, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deutsche Telekom Research and Development Laboratories, Berlin, Germany","institution_ids":["https://openalex.org/I4210093367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Bourlard","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","Swiss Federal Institute of Technology, Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Swiss Federal Institute of Technology, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.3992,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.98143093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"18","issue":"6","first_page":"1094","last_page":"1106"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.787847638130188},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7793178558349609},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6509536504745483},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6179826259613037},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5643786787986755},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.5431408882141113},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4993429183959961},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4747141897678375},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.45387688279151917},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44270190596580505},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4289158582687378},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41884803771972656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3466205894947052},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.09144869446754456}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.787847638130188},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7793178558349609},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6509536504745483},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6179826259613037},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5643786787986755},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.5431408882141113},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4993429183959961},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4747141897678375},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.45387688279151917},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44270190596580505},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4289158582687378},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41884803771972656},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3466205894947052},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.09144869446754456},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tasl.2009.2023162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2023162","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.323.8109","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.323.8109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/reports/2008/haketa-rr-08-39.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146047","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:172010","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/172010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146047","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146047","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W88309612","https://openalex.org/W159349026","https://openalex.org/W169882265","https://openalex.org/W190289757","https://openalex.org/W197151588","https://openalex.org/W219896985","https://openalex.org/W811578723","https://openalex.org/W1534536260","https://openalex.org/W1537192855","https://openalex.org/W1553004968","https://openalex.org/W1616590059","https://openalex.org/W1792764070","https://openalex.org/W1802155944","https://openalex.org/W1815165135","https://openalex.org/W1953567190","https://openalex.org/W1974556460","https://openalex.org/W1993197592","https://openalex.org/W2017399882","https://openalex.org/W2024119716","https://openalex.org/W2034537249","https://openalex.org/W2043422002","https://openalex.org/W2090861223","https://openalex.org/W2095635999","https://openalex.org/W2103203308","https://openalex.org/W2107223151","https://openalex.org/W2109560142","https://openalex.org/W2125838338","https://openalex.org/W2133924365","https://openalex.org/W2134659216","https://openalex.org/W2150907703","https://openalex.org/W2151156631","https://openalex.org/W2165712214","https://openalex.org/W2166810516","https://openalex.org/W2594610113","https://openalex.org/W4285719527","https://openalex.org/W6606397585","https://openalex.org/W6607679263","https://openalex.org/W6607944266","https://openalex.org/W6631925876","https://openalex.org/W6638352220"],"related_works":["https://openalex.org/W2153098279","https://openalex.org/W161037869","https://openalex.org/W2076543106","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W4286643620","https://openalex.org/W2523437662","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456"],"abstract_inverted_index":{"Using":[0],"phone":[1,26,44,108,136],"posterior":[2,68,122],"probabilities":[3,56],"has":[4],"been":[5,176],"increasingly":[6],"explored":[7],"for":[8,22],"improving":[9],"automatic":[10],"speech":[11],"recognition":[12,195],"(ASR)":[13],"systems.":[14],"In":[15,40,82],"this":[16],"paper,":[17],"we":[18],"propose":[19,156],"two":[20],"approaches":[21],"hierarchically":[23],"enhancing":[24],"these":[25],"posteriors,":[27],"by":[28,95],"integrating":[29,70],"long":[30],"acoustic":[31],"context,":[32],"as":[33,35,54,161,164],"well":[34],"phonetic":[36,76,113],"and":[37,77,80,104,152,181,193],"lexical":[38,78],"knowledge.":[39,114],"the":[41,83,89,107,121,125,130,140,143,158,168],"first":[42],"approach,":[43,85],"posteriors":[45,92,145,160],"estimated":[46],"with":[47],"a":[48,96],"multilayer":[49],"perceptron":[50],"(MLP),":[51],"are":[52,93,112],"used":[53],"emission":[55],"in":[57,99,120,134,146,187,190],"hidden":[58],"Markov":[59],"model":[60],"(HMM)":[61],"forward-backward":[62],"recursions.":[63],"This":[64],"yields":[65],"new":[66],"enhanced":[67,135,144,159],"estimates":[69],"HMM":[71],"topological":[72],"constraints":[73],"(encoding":[74],"specific":[75],"knowledge),":[79],"context.":[81],"second":[84,131],"temporal":[86],"contexts":[87],"of":[88,129,142],"regular":[90,169],"MLP":[91,170],"postprocessed":[94],"secondary":[97],"MLP,":[98,132],"order":[100],"to":[101,167],"learn":[102],"inter-":[103],"intra-dependencies":[105],"between":[106],"posteriors.":[109,137,171],"These":[110],"dependencies":[111],"The":[115,172],"learned":[116],"knowledge":[117],"is":[118],"integrated":[119],"estimation":[123],"during":[124],"inference":[126],"(forward":[127],"pass)":[128],"resulting":[133,186],"We":[138,155],"investigate":[139],"use":[141],"hybrid":[147],"HMM/artificial":[148],"neural":[149],"network":[150],"(ANN)":[151],"Tandem":[153],"configurations.":[154],"using":[157],"replacement,":[162],"or":[163],"complementary":[165],"evidences":[166],"proposed":[173],"methods":[174],"have":[175],"tested":[177],"on":[178],"different":[179],"small":[180],"large":[182],"vocabulary":[183],"databases,":[184],"always":[185],"consistent":[188],"improvements":[189],"frame,":[191],"phone,":[192],"word":[194],"rates.":[196]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}