{"id":"https://openalex.org/W2012190582","doi":"https://doi.org/10.1109/asru.2013.6707752","title":"Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition","display_name":"Impact of deep MLP architecture on different acoustic modeling techniques for under-resourced speech recognition","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2012190582","doi":"https://doi.org/10.1109/asru.2013.6707752","mag":"2012190582"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/98231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037750159","display_name":"David Imseng","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":true,"raw_author_name":"David Imseng","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076409146","display_name":"Petr Motl\u00ed\u010dek","orcid":"https://orcid.org/0000-0001-6467-1119"},"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":"Petr Motlicek","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081808619","display_name":"Philip N. Garner","orcid":"https://orcid.org/0000-0002-0814-1348"},"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":"Philip N. Garner","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., 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, Martigny, Switzerland","IDIAP Res. Inst., Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"IDIAP Res. Inst., Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5037750159"],"corresponding_institution_ids":["https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":5.7708,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.95764968,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"332","last_page":"337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.9043533802032471},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505895495414734},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.648399829864502},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6090130805969238},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.576083242893219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5620210766792297},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5395829081535339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5391095280647278},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.5141382813453674},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5057938098907471},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46034789085388184},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.4452216625213623},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3505249619483948},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.09725502133369446}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9043533802032471},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505895495414734},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.648399829864502},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6090130805969238},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.576083242893219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5620210766792297},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5395829081535339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5391095280647278},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.5141382813453674},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5057938098907471},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46034789085388184},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.4452216625213623},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3505249619483948},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.09725502133369446},{"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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/asru.2013.6707752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.tind.io:192452","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/98231","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":"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.tind.io:192452","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/98231","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":"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W29952999","https://openalex.org/W102093577","https://openalex.org/W119121225","https://openalex.org/W943204654","https://openalex.org/W1534441687","https://openalex.org/W1556037242","https://openalex.org/W1574284142","https://openalex.org/W1993660824","https://openalex.org/W1993882792","https://openalex.org/W2078573383","https://openalex.org/W2108776455","https://openalex.org/W2113342254","https://openalex.org/W2120209245","https://openalex.org/W2123798005","https://openalex.org/W2131042651","https://openalex.org/W2146168991","https://openalex.org/W2160815625","https://openalex.org/W6601192135","https://openalex.org/W6604932904","https://openalex.org/W6633468024","https://openalex.org/W6681612289","https://openalex.org/W7019186987"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4285282705","https://openalex.org/W161037869","https://openalex.org/W2076543106","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W2098747959","https://openalex.org/W2523437662"],"abstract_inverted_index":{"Posterior":[0],"based":[1,9,38,97],"acoustic":[2],"modeling":[3],"techniques":[4],"such":[5],"as":[6,73,75,87],"Kullback-Leibler":[7],"divergence":[8],"HMM":[10],"(KL-HMM)":[11],"and":[12,106,121],"Tandem":[13],"are":[14],"able":[15],"to":[16],"exploit":[17],"out-of-language":[18],"data":[19],"through":[20],"posterior":[21,37,85],"features,":[22],"estimated":[23],"by":[24,54],"a":[25,48,55,77,94,99,113,125],"Multi-Layer":[26],"Perceptron":[27],"(MLP).":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"investigate":[33],"the":[34,41,84,117],"performance":[35],"of":[36,43,66],"approaches":[39],"in":[40],"context":[42],"under-resourced":[44],"speech":[45],"recognition":[46],"when":[47],"standard":[49],"three-layer":[50],"MLP":[51,61,120],"is":[52],"replaced":[53],"deeper":[56,60],"five-layer":[57],"MLP.":[58],"The":[59,90],"architecture":[62],"yields":[63],"similar":[64],"gains":[65],"about":[67],"15%":[68],"(relative)":[69],"for":[70,76],"Tandem,":[71],"KL-HMM":[72,96],"well":[74],"hybrid":[78,114],"HMM/MLP":[79],"system":[80,115,129],"that":[81],"directly":[82],"uses":[83],"estimates":[86],"emission":[88],"probabilities.":[89],"best":[91],"performing":[92],"system,":[93],"bilingual":[95,119],"on":[98,104,132],"deep":[100],"MLP,":[101],"jointly":[102],"trained":[103,131],"Afrikaans":[105,133],"Dutch":[107],"data,":[108],"performs":[109],"13%":[110],"better":[111,123],"than":[112,124],"using":[116],"same":[118],"26%":[122],"subspace":[126],"Gaussian":[127],"mixture":[128],"only":[130],"data.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
