{"id":"https://openalex.org/W2153839310","doi":"https://doi.org/10.1109/icassp.2008.4518547","title":"Hierarchical integration of phonetic and lexical knowledge in phone posterior estimation","display_name":"Hierarchical integration of phonetic and lexical knowledge in phone posterior estimation","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2153839310","doi":"https://doi.org/10.1109/icassp.2008.4518547","mag":"2153839310"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518547","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,"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":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146045","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/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":"Hamed Ketabdar","raw_affiliation_strings":["IDIAP Research Institute, Swiss Federal Institute of Technology, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Swiss Federal Institute of Technology, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"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":"Herve Bourlard","raw_affiliation_strings":["IDIAP Research Institute, Swiss Federal Institute of Technology, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDIAP Research Institute, Swiss Federal Institute of Technology, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":4.537,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95697028,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4065","last_page":"4068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9995999932289124,"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":0.9976000189781189,"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":0.8188392519950867},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7108120322227478},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.700640857219696},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6754096746444702},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5422161817550659},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4580880403518677},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.45228713750839233},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4519767463207245},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4188113510608673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41765671968460083},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4169090986251831},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3430328369140625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32417190074920654},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3171841502189636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10328122973442078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188392519950867},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7108120322227478},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.700640857219696},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6754096746444702},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5422161817550659},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4580880403518677},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.45228713750839233},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4519767463207245},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4188113510608673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41765671968460083},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4169090986251831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3430328369140625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32417190074920654},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3171841502189636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10328122973442078},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2008.4518547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518547","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,"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":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:146045","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146045","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.tind.io:146045","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/46808","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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146045","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146045","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","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W159349026","https://openalex.org/W197151588","https://openalex.org/W811578723","https://openalex.org/W1553004968","https://openalex.org/W1802155944","https://openalex.org/W1953567190","https://openalex.org/W2043422002","https://openalex.org/W2165712214","https://openalex.org/W2594610113","https://openalex.org/W4285719527","https://openalex.org/W6606397585"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2153098279","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W161037869","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W36113703","https://openalex.org/W2340308015"],"abstract_inverted_index":{"Phone":[0],"posteriors":[1,61,158],"has":[2,185],"recently":[3],"quite":[4],"often":[5],"used":[6,75,162],"(as":[7],"additional":[8],"features":[9],"or":[10,179],"as":[11,76,149,172],"local":[12],"scores)":[13],"to":[14,78,94,119],"improve":[15],"state-of-the-art":[16],"automatic":[17],"speech":[18],"recognition":[19,210],"(ASR)":[20],"systems.":[21,181],"Usually,":[22],"better":[23,28],"phone":[24,46,60,97,164,174,207],"posterior":[25,98,124],"estimates":[26],"yield":[27],"ASR":[29],"performance.":[30],"In":[31,55],"the":[32,56,96,107,112,169],"present":[33,36],"paper":[34],"we":[35],"some":[37],"initial,":[38],"yet":[39],"promising,":[40],"work":[41],"towards":[42],"hierarchically":[43],"improving":[44],"these":[45],"posteriors,":[47,175],"by":[48,136],"implicitly":[49],"integrating":[50],"phonetic":[51],"and":[52,68,92,126,152,165,192,202,208],"lexical":[53,153],"knowledge.":[54,154],"approach":[57],"investigated":[58],"here,":[59],"estimated":[62],"with":[63],"a":[64,79,83,120,133,139],"multilayer":[65],"perceptron":[66],"(MLP)":[67],"short":[69],"(9":[70],"frames)":[71],"temporal":[72,85,141],"context,":[73],"are":[74],"input":[77],"second":[80],"MLP,":[81,111],"spanning":[82],"longer":[84],"context":[86],"(e.g.":[87],"19":[88],"frames":[89],"of":[90,109,122],"posteriors)":[91],"trained":[93],"refine":[95],"estimates.":[99],"The":[100,155,182],"rationale":[101],"behind":[102],"this":[103],"is":[104,115],"that":[105],"at":[106,138],"output":[108],"every":[110],"information":[113],"stream":[114],"getting":[116],"simpler":[117,134],"(converging":[118],"sequence":[121],"binary":[123],"vectors),":[125],"can":[127,146,159],"thus":[128],"be":[129,147,161],"further":[130],"processed":[131],"(using":[132],"classifier)":[135],"looking":[137],"larger":[140],"window.":[142],"Longer":[143],"term":[144],"dependencies":[145],"interpreted":[148],"phonetic,":[150],"sub-lexical":[151],"resulting":[156,199],"enhanced":[157],"then":[160],"for":[163],"word":[166,209],"recognition,":[167],"in":[168,176,200,205],"same":[170],"way":[171],"regular":[173],"hybrid":[177],"HMM/ANN":[178],"Tandem":[180],"proposed":[183],"method":[184],"been":[186],"tested":[187],"on":[188],"TIMIT,":[189],"OGI":[190],"Numbers":[191],"Conversational":[193],"Telephone":[194],"Speech":[195],"(CTS)":[196],"databases,":[197],"always":[198],"consistent":[201],"significant":[203],"improvements":[204],"both":[206],"rates.":[211]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}