{"id":"https://openalex.org/W2397534874","doi":"https://doi.org/10.21437/interspeech.2013-45","title":"Modular combination of deep neural networks for acoustic modeling","display_name":"Modular combination of deep neural networks for acoustic modeling","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2397534874","doi":"https://doi.org/10.21437/interspeech.2013-45","mag":"2397534874"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069183549","display_name":"Jonas Gehring","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jonas Gehring","raw_affiliation_strings":["Interactive Systems Lab, Karlsruhe Institute of Technology; Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022491076","display_name":"Wonkyum Lee","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":"Wonkyum Lee","raw_affiliation_strings":["Silicon Valley Campus, Carnegie Mellon University; USA"],"affiliations":[{"raw_affiliation_string":"Silicon Valley Campus, Carnegie Mellon University; USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034910585","display_name":"Kevin Kilgour","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kevin Kilgour","raw_affiliation_strings":["Interactive Systems Lab, Karlsruhe Institute of Technology; Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028182466","display_name":"Ian Lane","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":"Ian Lane","raw_affiliation_strings":["Silicon Valley Campus, Carnegie Mellon University; USA"],"affiliations":[{"raw_affiliation_string":"Silicon Valley Campus, Carnegie Mellon University; USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":["Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","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"]},{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Lab, Karlsruhe Institute of Technology; Germany","institution_ids":["https://openalex.org/I102335020"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University; Pittsburgh, PA; USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5069183549"],"corresponding_institution_ids":["https://openalex.org/I102335020"],"apc_list":null,"apc_paid":null,"fwci":11.3674,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.98338225,"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":"94","last_page":"98"},"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/T11309","display_name":"Music and Audio Processing","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.814584493637085},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6591439843177795},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6543015241622925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6421443223953247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6196218729019165},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5882092714309692},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.573543131351471},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5684522986412048},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5290067791938782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181509256362915},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5088591575622559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4629799723625183},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4482986629009247},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44473716616630554},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.42233896255493164},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.33176302909851074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07893258333206177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814584493637085},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6591439843177795},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6543015241622925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6421443223953247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6196218729019165},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5882092714309692},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.573543131351471},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5684522986412048},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5290067791938782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181509256362915},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5088591575622559},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4629799723625183},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4482986629009247},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44473716616630554},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.42233896255493164},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.33176302909851074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07893258333206177},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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:10.21437/interspeech.2013-45","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-45","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.1799","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.1799","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/modular_is13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W82501063","https://openalex.org/W1495547083","https://openalex.org/W1970088388","https://openalex.org/W1993882792","https://openalex.org/W1997449813","https://openalex.org/W2072349636","https://openalex.org/W2106051978","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2145094598","https://openalex.org/W2147768505","https://openalex.org/W2156373089","https://openalex.org/W2159948109","https://openalex.org/W2160306971","https://openalex.org/W2161893161","https://openalex.org/W2165712214","https://openalex.org/W2172097686","https://openalex.org/W2394932179","https://openalex.org/W2997574889"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2109916967","https://openalex.org/W2890297197","https://openalex.org/W2101697354","https://openalex.org/W1538193578","https://openalex.org/W3206636855","https://openalex.org/W1538606284","https://openalex.org/W2373874059"],"abstract_inverted_index":{"In":[0,38],"this":[1,49],"work,":[2],"we":[3],"propose":[4],"a":[5,21,39,55,61,70,78,100,127,136],"modular":[6,118],"combination":[7],"of":[8,12,33,85,96,112],"two":[9],"pop-ular":[10],"applications":[11],"neural":[13,23],"networks":[14],"to":[15,27,93,124],"large-vocabulary":[16],"con-tinuous":[17],"speech":[18],"recognition.":[19],"First,":[20],"deep":[22,71],"network":[24,50,88],"is":[25,43,51,67,133],"trained":[26],"extract":[28],"bottleneck":[29,87,106],"features":[30,107],"from":[31,126],"frames":[32,98],"mel":[34],"scale":[35],"filterbank":[36],"coefficients.":[37],"similar":[40],"way":[41],"as":[42,54],"usually":[44],"done":[45],"for":[46,60],"GMM/HMM":[47],"systems,":[48],"then":[52],"applied":[53,92],"non-linear":[56],"discriminative":[57],"feature-space":[58],"transformation":[59],"hybrid":[62],"setup":[63],"where":[64,82],"acoustic":[65,122],"modeling":[66],"performed":[68],"by":[69],"belief":[72],"network.":[73],"This":[74],"effectively":[75],"results":[76],"in":[77,99],"very":[79],"large":[80],"network,":[81],"the":[83,86,109,117,121],"layers":[84],"are":[89],"fixed":[90],"and":[91,115,139],"suc-cessive":[94],"windows":[95],"feature":[97],"time-delay":[101],"fashion.":[102],"We":[103],"show":[104],"that":[105,116],"improve":[108],"recognition":[110],"perfor-mance":[111],"DBN/HMM":[113],"hybrids,":[114],"combina-tion":[119],"enables":[120],"model":[123],"benefit":[125],"larger":[128],"tempo-ral":[129],"context.":[130],"Our":[131],"architecture":[132],"evaluated":[134],"on":[135],"recently":[137],"released":[138],"challenging":[140],"Tagalog":[141],"corpus":[142],"containing":[143],"conversational":[144],"tele-phone":[145],"speech.":[146]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}