{"id":"https://openalex.org/W2091432990","doi":"https://doi.org/10.1109/icassp.2013.6639344","title":"New types of deep neural network learning for speech recognition and related applications: an overview","display_name":"New types of deep neural network learning for speech recognition and related applications: an overview","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2091432990","doi":"https://doi.org/10.1109/icassp.2013.6639344","mag":"2091432990"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geoffrey Hinton","raw_affiliation_strings":["University of Toronto, ONT, Canada","University of Toronto, Toronto, On, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto, ONT, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"University of Toronto, Toronto, On, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1207,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8599","last_page":"8603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7617058753967285},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5836590528488159},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5780797600746155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093635320663452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48066699504852295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7617058753967285},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5836590528488159},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5780797600746155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093635320663452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48066699504852295}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639344","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.1123","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.1123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://learning.cs.toronto.edu/~hinton/absps/overview13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W196761320","https://openalex.org/W217970951","https://openalex.org/W299739017","https://openalex.org/W1408639475","https://openalex.org/W1496929357","https://openalex.org/W1553004968","https://openalex.org/W1904365287","https://openalex.org/W1978660892","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W2014641584","https://openalex.org/W2022011789","https://openalex.org/W2022799064","https://openalex.org/W2027915610","https://openalex.org/W2035424729","https://openalex.org/W2036242736","https://openalex.org/W2048060899","https://openalex.org/W2062227835","https://openalex.org/W2074818733","https://openalex.org/W2076794394","https://openalex.org/W2097998348","https://openalex.org/W2100495367","https://openalex.org/W2102486516","https://openalex.org/W2108563286","https://openalex.org/W2110871230","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2120480077","https://openalex.org/W2125964738","https://openalex.org/W2130414229","https://openalex.org/W2131241448","https://openalex.org/W2136922672","https://openalex.org/W2143612262","https://openalex.org/W2144792281","https://openalex.org/W2146502635","https://openalex.org/W2147768505","https://openalex.org/W2149600041","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2168013545","https://openalex.org/W2168231600","https://openalex.org/W2171928131","https://openalex.org/W2184045248","https://openalex.org/W2184188583","https://openalex.org/W2188183693","https://openalex.org/W2252143850","https://openalex.org/W2253807446","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2403195671","https://openalex.org/W2913340405","https://openalex.org/W2914746235","https://openalex.org/W2950789693","https://openalex.org/W6608133726","https://openalex.org/W6628131027","https://openalex.org/W6653960356","https://openalex.org/W6674385629","https://openalex.org/W6675672627","https://openalex.org/W6678242812","https://openalex.org/W6678911119","https://openalex.org/W6679053740","https://openalex.org/W6681435938","https://openalex.org/W6684191040","https://openalex.org/W6684859321","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"provide":[4],"an":[5],"overview":[6,59],"of":[7,23,60,73,84,100,118],"the":[8,15,37,42,61,97],"invited":[9],"and":[10,31,88,115],"contributed":[11],"papers":[12,62],"presented":[13,63],"at":[14,18],"special":[16,66],"session":[17,67],"ICASSP-2013,":[19],"entitled":[20],"\u201cNew":[21],"Types":[22],"Deep":[24],"Neural":[25],"Network":[26],"Learning":[27],"for":[28,111],"Speech":[29],"Recognition":[30],"Related":[32],"Applications,\u201d":[33],"as":[34],"organized":[35,69],"by":[36],"authors.":[38],"We":[39],"also":[40],"describe":[41],"historical":[43],"context":[44],"in":[45,64],"which":[46],"acoustic":[47],"models":[48],"based":[49],"on":[50],"deep":[51,75,101,112,130],"neural":[52,85,102,113,131],"networks":[53,132],"have":[54],"been":[55],"developed.":[56],"The":[57],"technical":[58],"our":[65],"is":[68],"into":[70],"five":[71],"ways":[72,94,107,117],"improving":[74],"learning":[76],"methods:":[77],"(1)":[78],"better":[79,82,89,93],"optimization;":[80],"(2)":[81],"types":[83],"activation":[86],"function":[87],"network":[90],"architectures;":[91],"(3)":[92],"to":[95,108],"determine":[96],"myriad":[98],"hyper-parameters":[99],"networks;":[103,114],"(4)":[104],"more":[105,126],"appropriate":[106],"preprocess":[109],"speech":[110],"(5)":[116],"leveraging":[119],"multiple":[120],"languages":[121],"or":[122],"dialects":[123],"that":[124],"are":[125],"easily":[127],"achieved":[128],"with":[129,134],"than":[133],"Gaussian":[135],"mixture":[136],"models.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":119},{"year":2022,"cited_by_count":123},{"year":2021,"cited_by_count":163},{"year":2020,"cited_by_count":154},{"year":2019,"cited_by_count":144},{"year":2018,"cited_by_count":139},{"year":2017,"cited_by_count":93},{"year":2016,"cited_by_count":61},{"year":2015,"cited_by_count":48},{"year":2014,"cited_by_count":34},{"year":2013,"cited_by_count":9}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}