{"id":"https://openalex.org/W2089917322","doi":"https://doi.org/10.1109/asru.2013.6707763","title":"Deep maxout networks for low-resource speech recognition","display_name":"Deep maxout networks for low-resource speech recognition","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2089917322","doi":"https://doi.org/10.1109/asru.2013.6707763","mag":"2089917322"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707763","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","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/Deep_maxout_networks_for_low-resource_speech_recognition/6473306","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":true,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":["Language Technologies Institute, Carnegie Mellon University","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086192353","display_name":"Shourabh Rawat","orcid":"https://orcid.org/0009-0000-0160-3741"},"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":"Shourabh Rawat","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003251887"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":25.7002,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.99573267,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"398","last_page":"403"},"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":0.9977999925613403,"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":0.9950000047683716,"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":0.7853454351425171},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6655360460281372},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5755679607391357},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5450839996337891},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5418525338172913},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5021505355834961},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48753902316093445},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4752114713191986},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38263899087905884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34261125326156616},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.07846343517303467}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853454351425171},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6655360460281372},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5755679607391357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450839996337891},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5418525338172913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5021505355834961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48753902316093445},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4752114713191986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38263899087905884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34261125326156616},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.07846343517303467},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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":6,"locations":[{"id":"doi:10.1109/asru.2013.6707763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707763","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:figshare.com:article/6473306","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Deep_maxout_networks_for_low-resource_speech_recognition/6473306","pdf_url":"https://figshare.com/articles/Deep_maxout_networks_for_low-resource_speech_recognition/6473306","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":"pmh:oai:repository.cmu.edu:lti-1084","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1084&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"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/r1/6473306","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:10.1.1.710.2557","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.2557","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/maxout_final_asru13_V3.pdf","raw_type":"text"},{"id":"doi:10.1184/r1/6473306.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473306.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":[],"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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473306","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Deep_maxout_networks_for_low-resource_speech_recognition/6473306","pdf_url":"https://figshare.com/articles/Deep_maxout_networks_for_low-resource_speech_recognition/6473306","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":[{"score":0.49000000953674316,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2089917322.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W17156489","https://openalex.org/W44815768","https://openalex.org/W1524333225","https://openalex.org/W1904365287","https://openalex.org/W1970088388","https://openalex.org/W1970890968","https://openalex.org/W1974205368","https://openalex.org/W1981706894","https://openalex.org/W2025198378","https://openalex.org/W2025487094","https://openalex.org/W2062227835","https://openalex.org/W2090764203","https://openalex.org/W2093794678","https://openalex.org/W2112984492","https://openalex.org/W2120209245","https://openalex.org/W2123237149","https://openalex.org/W2145094598","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2294059674","https://openalex.org/W2397534874","https://openalex.org/W2997574889","https://openalex.org/W6600718888","https://openalex.org/W6601785968","https://openalex.org/W6631362777","https://openalex.org/W6656619859","https://openalex.org/W6681096077","https://openalex.org/W6712029055"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2953234277","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W2962734882","https://openalex.org/W2185726654","https://openalex.org/W1034159276"],"abstract_inverted_index":{"As":[0],"a":[1],"feed-forward":[2],"architecture,":[3],"the":[4,24,43,80],"recently":[5],"proposed":[6],"maxout":[7,28,71],"networks":[8,29],"integrate":[9],"dropout":[10],"naturally":[11],"and":[12,60,64,114],"show":[13,98],"state-of-the-art":[14],"results":[15],"on":[16,42],"various":[17],"computer":[18],"vision":[19],"datasets.":[20],"This":[21],"paper":[22],"investigates":[23],"application":[25],"of":[26,46,70,86,94],"deep":[27],"(DMNs)":[30],"to":[31,58,110],"large":[32],"vocabulary":[33],"continuous":[34],"speech":[35,103],"recognition":[36,104],"(LVCSR)":[37],"tasks.":[38],"Our":[39],"focus":[40],"is":[41],"particular":[44],"advantage":[45],"DMNs":[47,57,87,100,107],"under":[48,91],"low-resource":[49,102],"conditions":[50],"with":[51],"limited":[52],"transcribed":[53],"speech.":[54],"We":[55],"extend":[56],"hybrid":[59],"bottleneck":[61],"feature":[62,120],"systems,":[63],"explore":[65],"optimal":[66],"network":[67],"structures":[68],"(number":[69],"layers,":[72],"pooling":[73],"strategy,":[74],"etc)":[75],"for":[76],"both":[77],"setups.":[78],"On":[79],"newly":[81],"released":[82],"Babel":[83],"corpus,":[84],"behaviors":[85],"are":[88],"extensively":[89],"studied":[90],"different":[92],"levels":[93],"data":[95],"availability.":[96],"Experiments":[97],"that":[99],"improve":[101],"significantly.":[105],"Moreover,":[106],"introduce":[108],"sparsity":[109],"their":[111],"hidden":[112],"activations":[113],"thus":[115],"can":[116],"act":[117],"as":[118],"sparse":[119],"extractors.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":17}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}