{"id":"https://openalex.org/W2409489983","doi":"https://doi.org/10.1109/lsp.2016.2589962","title":"Deep CNNs Along the Time Axis With Intermap Pooling for Robustness to Spectral Variations","display_name":"Deep CNNs Along the Time Axis With Intermap Pooling for Robustness to Spectral Variations","publication_year":2016,"publication_date":"2016-07-11","ids":{"openalex":"https://openalex.org/W2409489983","doi":"https://doi.org/10.1109/lsp.2016.2589962","mag":"2409489983"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2016.2589962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2016.2589962","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1606.03207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054334046","display_name":"Hwaran Lee","orcid":"https://orcid.org/0000-0002-3773-4871"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hwaran Lee","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066858751","display_name":"Geonmin Kim","orcid":"https://orcid.org/0000-0002-9704-6843"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geonmin Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069332832","display_name":"Ho-Gyeong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-Gyeong Kim","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046336702","display_name":"Sang-Hoon Oh","orcid":"https://orcid.org/0000-0002-2195-9056"},"institutions":[{"id":"https://openalex.org/I3133486578","display_name":"Mokwon University","ror":"https://ror.org/01whq8m38","country_code":"KR","type":"education","lineage":["https://openalex.org/I3133486578"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sang-Hoon Oh","raw_affiliation_strings":["Division of Information and Communication Convergence Engineering, Mokwon University, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Division of Information and Communication Convergence Engineering, Mokwon University, Daejeon, South Korea","institution_ids":["https://openalex.org/I3133486578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100616676","display_name":"Soo-Young Lee","orcid":"https://orcid.org/0000-0003-0776-5084"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soo-Young Lee","raw_affiliation_strings":["School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5054334046"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.7774,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89135331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":"10","first_page":"1310","last_page":"1314"},"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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/pooling","display_name":"Pooling","score":0.8949124813079834},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.809115469455719},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7375617027282715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180803418159485},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6815146207809448},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6543118953704834},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.591570258140564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5677065253257751},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4658074975013733},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4323844909667969},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4323250353336334},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42462122440338135},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20339179039001465}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8949124813079834},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.809115469455719},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7375617027282715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180803418159485},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6815146207809448},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6543118953704834},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.591570258140564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5677065253257751},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4658074975013733},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4323844909667969},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4323250353336334},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42462122440338135},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20339179039001465},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2016.2589962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2016.2589962","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1606.03207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.03207","pdf_url":"https://arxiv.org/pdf/1606.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1606.03207","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.03207","pdf_url":"https://arxiv.org/pdf/1606.03207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1524333225","https://openalex.org/W1686810756","https://openalex.org/W1965192788","https://openalex.org/W1985371235","https://openalex.org/W1985466488","https://openalex.org/W1993882792","https://openalex.org/W1995562189","https://openalex.org/W2005708641","https://openalex.org/W2024490156","https://openalex.org/W2032076168","https://openalex.org/W2077635320","https://openalex.org/W2079623482","https://openalex.org/W2094384715","https://openalex.org/W2105869280","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2117671523","https://openalex.org/W2121903223","https://openalex.org/W2124486835","https://openalex.org/W2125964738","https://openalex.org/W2140262144","https://openalex.org/W2143612262","https://openalex.org/W2146672645","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2188183693","https://openalex.org/W2198724430","https://openalex.org/W2293634267","https://openalex.org/W2294059674","https://openalex.org/W2295119550","https://openalex.org/W2401752152","https://openalex.org/W2402146185","https://openalex.org/W2963490782","https://openalex.org/W6603931906","https://openalex.org/W6631362777","https://openalex.org/W6639288305","https://openalex.org/W6676071220","https://openalex.org/W6678353412","https://openalex.org/W6696761078","https://openalex.org/W6697090674","https://openalex.org/W6712930963","https://openalex.org/W6712947341"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W2810679507","https://openalex.org/W2964954556"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"with":[4,28,147],"convolutional":[5],"and":[6,107],"pooling":[7,61],"operations":[8],"along":[9,46],"the":[10,31,47,56,81,84,93,112,127,135,139],"frequency":[11,20],"axis":[12,49],"have":[13],"been":[14],"proposed":[15,94],"to":[16,19,30,64,100],"attain":[17],"invariance":[18],"shifts":[21],"of":[22,58,87,104,111,132,138],"features.":[23],"However,":[24],"this":[25,40,68],"is":[26,50,116,145],"inappropriate":[27],"regard":[29],"fact":[32],"that":[33,44],"acoustic":[34],"features":[35],"vary":[36],"in":[37,71],"frequency.":[38],"In":[39,67],"paper,":[41],"we":[42],"contend":[43],"convolution":[45],"time":[48],"more":[51],"effective.":[52],"We":[53],"also":[54],"propose":[55],"addition":[57],"an":[59],"intermap":[60],"(IMP)":[62],"layer":[63,82],"deep":[65],"CNNs.":[66],"layer,":[69],"filters":[70],"each":[72,88],"group":[73],"extract":[74],"common":[75],"but":[76],"spectrally":[77],"variant":[78],"features,":[79],"then":[80],"pools":[83],"feature":[85],"maps":[86],"group.":[89],"As":[90],"a":[91,130],"result,":[92],"IMP":[95,113],"CNN":[96,114],"can":[97],"achieve":[98],"insensitivity":[99],"spectral":[101],"variations":[102],"characteristic":[103],"different":[105],"speakers":[106],"utterances.":[108],"The":[109],"effectiveness":[110],"architecture":[115,128],"demonstrated":[117],"on":[118,134],"several":[119],"LVCSR":[120],"tasks.":[121],"Even":[122],"without":[123],"speaker":[124],"adaptation":[125],"techniques,":[126],"achieved":[129],"WER":[131],"12.7%":[133],"SWB":[136],"part":[137],"Hub5'2000":[140],"evaluation":[141],"test":[142],"set,":[143],"which":[144],"competitive":[146],"other":[148],"state-of-the-art":[149],"methods.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}