{"id":"https://openalex.org/W2084253266","doi":"https://doi.org/10.1109/icassp.2010.5495121","title":"Analysis of phone posterior feature space exploiting class-specific sparsity and MLP-based similarity measure","display_name":"Analysis of phone posterior feature space exploiting class-specific sparsity and MLP-based similarity measure","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2084253266","doi":"https://doi.org/10.1109/icassp.2010.5495121","mag":"2084253266"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063249055","display_name":"Afsaneh Asaei","orcid":"https://orcid.org/0000-0002-1917-601X"},"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":"Afsaneh Asaei","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076663045","display_name":"Benjamin Picart","orcid":null},"institutions":[{"id":"https://openalex.org/I130929987","display_name":"University of Mons","ror":"https://ror.org/02qnnz951","country_code":"BE","type":"education","lineage":["https://openalex.org/I130929987"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Benjamin Picart","raw_affiliation_strings":["TCTS Lab, Facult\u00e9 Polytechnique, Universit\u00e8 de Mons, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCTS Lab, Facult\u00e9 Polytechnique, Universit\u00e8 de Mons, Belgium","institution_ids":["https://openalex.org/I130929987"]}]},{"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":"Herve Bourlard","raw_affiliation_strings":["Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]},{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7969,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.91229705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4886","last_page":"4889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9983000159263611,"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":0.9966999888420105,"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":0.7193876504898071},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7061898112297058},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6560669541358948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6310244798660278},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6116400361061096},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5537322163581848},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5364006757736206},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5360335111618042},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5208702087402344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5098111033439636},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5072852969169617},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4769769608974457},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4729670584201813},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4645421504974365},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4542745053768158},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.42981263995170593},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4215627610683441},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.41474050283432007},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21979981660842896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7193876504898071},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7061898112297058},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6560669541358948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6310244798660278},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6116400361061096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5537322163581848},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5364006757736206},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5360335111618042},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5208702087402344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098111033439636},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5072852969169617},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4769769608974457},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4729670584201813},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4645421504974365},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4542745053768158},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.42981263995170593},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4215627610683441},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.41474050283432007},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21979981660842896},{"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/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2010.5495121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495121","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.172.4215","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.172.4215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://tcts.fpms.ac.be/publications/papers/2010/icassp2010_aabphb.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146704","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146704","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":null,"host_organization_name":null,"host_organization_lineage":[],"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:orbi.umons.ac.be:20.500.12907/41339","is_oa":false,"landing_page_url":"https://orbi.umons.ac.be/handle/20.500.12907/41339","pdf_url":null,"source":{"id":"https://openalex.org/S7407055454","display_name":"ORBi UMONS","issn_l":null,"issn":null,"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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings, 4886 - 4889 (2010-03-14)","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146704","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146704","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":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1553004968","https://openalex.org/W1573706465","https://openalex.org/W1590626692","https://openalex.org/W1601795611","https://openalex.org/W1663973292","https://openalex.org/W2115685217","https://openalex.org/W2165712214","https://openalex.org/W6629510986","https://openalex.org/W6634210920"],"related_works":["https://openalex.org/W2075383893","https://openalex.org/W2052112670","https://openalex.org/W2474633151","https://openalex.org/W2048014685","https://openalex.org/W3160080723","https://openalex.org/W2094250226","https://openalex.org/W2608303656","https://openalex.org/W4244110343","https://openalex.org/W2098258572","https://openalex.org/W2058900301"],"abstract_inverted_index":{"Class":[0],"posterior":[1,100,131],"distributions":[2],"have":[3],"recently":[4],"been":[5],"used":[6],"quite":[7],"successfully":[8],"in":[9,36,40,116],"Automatic":[10],"Speech":[11],"Recognition":[12],"(ASR),":[13],"either":[14],"for":[15],"frame":[16],"or":[17,21,69,88,138],"phone":[18,157],"level":[19],"classification":[20,68,158],"as":[22,141,143],"acoustic":[23,78,101],"features,":[24],"which":[25],"can":[26,108],"be":[27,57,109],"further":[28],"exploited":[29,110],"(usually":[30],"after":[31],"some":[32],"\u201cad":[33],"hoc\u201d":[34],"transformations)":[35],"different":[37],"classifiers":[38],"(e.g.,":[39],"Gaussian":[41],"Mixture":[42],"based":[43],"HMMs).":[44],"In":[45,90],"the":[46,74,83,99,135,151],"present":[47],"paper,":[48,92],"we":[49,93],"show":[50],"preliminary":[51],"results":[52],"showing":[53,104],"that":[54],"it":[55],"may":[56],"possible":[58],"to":[59,82,111,134],"perform":[60],"speech":[61],"recognition":[62],"without":[63],"explicit":[64],"subword":[65,85],"unit":[66,86],"(phone)":[67],"likelihood":[70],"estimation,":[71],"simply":[72],"answering":[73],"question":[75],"whether":[76,129],"two":[77,130],"(posterior)":[79],"vectors":[80,132],"belong":[81,133],"same":[84,136],"class":[87,137],"not.":[89,139],"this":[91],"first":[94],"exhibit":[95],"specific":[96],"properties":[97,107],"of":[98],"space":[102],"before":[103,154],"how":[105],"those":[106],"reach":[112],"very":[113],"high":[114,142],"performance":[115],"deciding":[117],"(based":[118],"on":[119,150],"an":[120],"appropriate,":[121],"trained,":[122],"distance":[123],"metric,":[124],"and":[125],"hypothesis":[126],"testing":[127],"approaches)":[128],"Performance":[140],"90%":[144],"correct":[145],"decision":[146],"rates":[147],"are":[148],"reported":[149],"TIMIT":[152],"database,":[153],"reporting":[155],"kNN":[156],"rates.":[159]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}