{"id":"https://openalex.org/W587565084","doi":"https://doi.org/10.21437/interspeech.2014-205","title":"Improving language-universal feature extraction with deep maxout and convolutional neural networks","display_name":"Improving language-universal feature extraction with deep maxout and convolutional neural networks","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W587565084","doi":"https://doi.org/10.21437/interspeech.2014-205","mag":"587565084"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-205","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Improving_Language-Universal_Feature_Extraction_with_Deep_Maxout_and_Convolutional_Neural_Networks/6473417","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.8948,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92508717,"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":"800","last_page":"804"},"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":0.9988999962806702,"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":0.9980000257492065,"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":0.8484680652618408},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6617234945297241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6607102751731873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5568985342979431},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5549443960189819},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5409747958183289},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5407578349113464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4661470949649811},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45701247453689575},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42834222316741943},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.42724665999412537},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42320847511291504},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35628741979599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484680652618408},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6617234945297241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607102751731873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5568985342979431},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5549443960189819},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5409747958183289},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5407578349113464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4661470949649811},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45701247453689575},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42834222316741943},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.42724665999412537},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42320847511291504},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35628741979599},{"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":7,"locations":[{"id":"doi:10.21437/interspeech.2014-205","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1069","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1069&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473417","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.8047","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.8047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eymiao/pub/conv_draft_final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.974.7601","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.974.7601","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://repository.cmu.edu/cgi/viewcontent.cgi?article%3D1069%26context%3Dlti","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473417","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_Language-Universal_Feature_Extraction_with_Deep_Maxout_and_Convolutional_Neural_Networks/6473417","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473417.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473417.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473417","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Improving_Language-Universal_Feature_Extraction_with_Deep_Maxout_and_Convolutional_Neural_Networks/6473417","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W17156489","https://openalex.org/W44815768","https://openalex.org/W567546468","https://openalex.org/W596888916","https://openalex.org/W619799124","https://openalex.org/W655723668","https://openalex.org/W1661756259","https://openalex.org/W1904365287","https://openalex.org/W1968419113","https://openalex.org/W1970088388","https://openalex.org/W1986571466","https://openalex.org/W2004227461","https://openalex.org/W2025198378","https://openalex.org/W2025487094","https://openalex.org/W2026369565","https://openalex.org/W2062227835","https://openalex.org/W2067474491","https://openalex.org/W2089917322","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2130325614","https://openalex.org/W2133257461","https://openalex.org/W2145094598","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2156387975","https://openalex.org/W2160306971","https://openalex.org/W2167210642","https://openalex.org/W2188183693","https://openalex.org/W2294059674","https://openalex.org/W2295125894","https://openalex.org/W2397534874","https://openalex.org/W2402967400","https://openalex.org/W2585504920","https://openalex.org/W2962719052","https://openalex.org/W2964138484"],"related_works":["https://openalex.org/W2376954173","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W2129812225","https://openalex.org/W4290708361","https://openalex.org/W26527944","https://openalex.org/W2523799048","https://openalex.org/W2155620340"],"abstract_inverted_index":{"When":[0],"deployed":[1],"in":[2,108],"automated":[3],"speech":[4],"recognition":[5],"(ASR),":[6],"deep":[7],"neural":[8,79],"networks":[9],"(DNNs)":[10],"can":[11],"be":[12],"treated":[13],"as":[14,34],"a":[15,20,98],"complex":[16],"feature":[17,36,74,89],"extractor":[18],"plus":[19],"simple":[21],"linear":[22],"classifier.":[23],"Previous":[24],"work":[25],"has":[26],"investigated":[27],"the":[28,53,58,68,77,93,104,115,120,128],"utility":[29],"of":[30,71,95,103],"multilingual":[31],"DNNs":[32],"acting":[33],"language-universal":[35],"extractors":[37],"(LUFEs).":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,51],"explore":[43],"different":[44],"strategies":[45],"to":[46,85],"further":[47],"improve":[48],"LUFEs.":[49,118],"First,":[50],"replace":[52],"standard":[54],"sigmoid":[55],"nonlinearity":[56],"with":[57,114],"recently":[59],"proposed":[60,105],"maxout":[61,65],"units.":[62],"The":[63],"resulting":[64],"LUFEs":[66,96],"have":[67],"nice":[69],"property":[70],"generating":[72],"sparse":[73],"representations.":[75],"Second,":[76],"convolutional":[78],"network":[80],"(CNN)":[81],"architecture":[82],"is":[83],"applied":[84],"obtain":[86],"more":[87],"invariant":[88],"space.":[90],"We":[91],"evaluate":[92],"performance":[94],"on":[97,127],"cross-language":[99],"ASR":[100],"task.":[101],"Each":[102],"techniques":[106],"results":[107],"word":[109],"error":[110],"rate":[111],"reduction":[112],"compared":[113],"existing":[116],"DNN-based":[117],"Combining":[119],"two":[121],"methods":[122],"together":[123],"brings":[124],"additional":[125],"improvement":[126],"target":[129],"language.":[130]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}