{"id":"https://openalex.org/W2036242736","doi":"https://doi.org/10.1109/icassp.2013.6638952","title":"A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion","display_name":"A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2036242736","doi":"https://doi.org/10.1109/icassp.2013.6638952","mag":"2036242736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6638952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638952","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":"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/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":true,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"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/A5077733105","display_name":"Ossama Abdel\u2010Hamid","orcid":null},"institutions":[{"id":"https://openalex.org/I192455969","display_name":"York University","ror":"https://ror.org/05fq50484","country_code":"CA","type":"education","lineage":["https://openalex.org/I192455969"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ossama Abdel-Hamid","raw_affiliation_strings":["York University, Toronto, ONT, Canada","York University , Toronto , ON, Canada"],"affiliations":[{"raw_affiliation_string":"York University, Toronto, ONT, Canada","institution_ids":["https://openalex.org/I192455969"]},{"raw_affiliation_string":"York University , Toronto , ON, Canada","institution_ids":["https://openalex.org/I192455969"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100671324"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":30.17750873,"has_fulltext":false,"cited_by_count":188,"citation_normalized_percentile":{"value":0.99727119,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6669","last_page":"6673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9998000264167786,"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":0.7917935848236084},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7374173402786255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7160373330116272},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6928882002830505},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5956772565841675},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5939565896987915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5133568644523621},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4868263602256775},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4689609110355377},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4333533048629761},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3392621576786041},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3341487944126129},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15237605571746826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7917935848236084},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7374173402786255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7160373330116272},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6928882002830505},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5956772565841675},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5939565896987915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133568644523621},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4868263602256775},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4689609110355377},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4333533048629761},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3392621576786041},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3341487944126129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15237605571746826}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6638952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6638952","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W246799964","https://openalex.org/W1218987319","https://openalex.org/W1269046860","https://openalex.org/W1904365287","https://openalex.org/W1984541135","https://openalex.org/W1993882792","https://openalex.org/W2014641584","https://openalex.org/W2022011789","https://openalex.org/W2027915610","https://openalex.org/W2053001900","https://openalex.org/W2074818733","https://openalex.org/W2076794394","https://openalex.org/W2091432990","https://openalex.org/W2092684968","https://openalex.org/W2095168618","https://openalex.org/W2103283951","https://openalex.org/W2106051978","https://openalex.org/W2106347453","https://openalex.org/W2108597378","https://openalex.org/W2112796928","https://openalex.org/W2125964738","https://openalex.org/W2134557905","https://openalex.org/W2141778357","https://openalex.org/W2147768505","https://openalex.org/W2147860648","https://openalex.org/W2149600041","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2168013545","https://openalex.org/W2184045248","https://openalex.org/W2184188583","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2397277575","https://openalex.org/W2403195671","https://openalex.org/W2504108613","https://openalex.org/W2618530766","https://openalex.org/W6679053740","https://openalex.org/W6684191040","https://openalex.org/W6686207219"],"related_works":["https://openalex.org/W2962734882","https://openalex.org/W2185726654","https://openalex.org/W1034159276","https://openalex.org/W2899547849","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2994894110","https://openalex.org/W2092523626","https://openalex.org/W4377862891"],"abstract_inverted_index":{"We":[0],"develop":[1],"and":[2,57,109,139],"present":[3],"a":[4,63,71,94,136,156],"novel":[5],"deep":[6,72,89,170],"convolutional":[7,171],"neural":[8,67,172],"network":[9,68],"architecture,":[10],"where":[11],"heterogeneous":[12,107,166],"pooling":[13,37,108,167],"is":[14,39],"used":[15],"to":[16,69,75],"provide":[17],"constrained":[18],"frequency-shift":[19],"invariance":[20],"in":[21,132,155,168],"the":[22,36,97,103,113,133,169],"speech":[23,46,80,153],"spectrogram":[24],"while":[25],"minimizing":[26],"speech-class":[27],"confusion":[28],"induced":[29],"by":[30,41,62],"such":[31],"invariance.":[32],"The":[33,55],"design":[34],"of":[35,86,96,105,143],"layer":[38],"guided":[40],"domain":[42],"knowledge":[43],"about":[44,145],"how":[45],"classes":[47],"would":[48],"change":[49],"when":[50],"formant":[51],"frequencies":[52],"are":[53,60,91],"modified.":[54],"convolution":[56],"heterogeneous-pooling":[58],"layers":[59,85],"followed":[61],"fully":[64],"connected":[65],"multi-layer":[66],"form":[70],"architecture":[73],"interfaced":[74],"an":[76,121],"HMM":[77],"for":[78],"continuous":[79],"recognition.":[81],"During":[82],"training,":[83],"all":[84],"this":[87,128],"entire":[88],"net":[90],"regularized":[92],"using":[93,165],"variant":[95],"\"dropout\"":[98],"technique.":[99],"Experimental":[100],"evaluation":[101],"demonstrates":[102],"effectiveness":[104],"both":[106],"dropout":[110],"regularization.":[111],"On":[112],"TIMIT":[114],"phonetic":[115],"recognition":[116,154],"task,":[117],"we":[118],"have":[119],"achieved":[120],"18.7%":[122],"phone":[123],"error":[124,162],"rate,":[125],"lowest":[126],"on":[127,150],"standard":[129],"task":[130,159],"reported":[131],"literature":[134],"with":[135,140],"single":[137],"system":[138],"no":[141],"use":[142],"information":[144],"speaker":[146],"identity.":[147],"Preliminary":[148],"experiments":[149],"large":[151],"vocabulary":[152],"voice":[157],"search":[158],"also":[160],"show":[161],"rate":[163],"reduction":[164],"network.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":20},{"year":2014,"cited_by_count":22},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}