{"id":"https://openalex.org/W3015480556","doi":"https://doi.org/10.1109/icassp40776.2020.9053973","title":"SNDCNN: Self-Normalizing Deep CNNs with Scaled Exponential Linear Units for Speech Recognition","display_name":"SNDCNN: Self-Normalizing Deep CNNs with Scaled Exponential Linear Units for Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015480556","doi":"https://doi.org/10.1109/icassp40776.2020.9053973","mag":"3015480556"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5011008665","display_name":"Zhen Huang","orcid":"https://orcid.org/0000-0003-4819-373X"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhen Huang","raw_affiliation_strings":["Apple Inc.,USA","Apple Inc., USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc.,USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc., USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110640042","display_name":"Tim Ng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Ng","raw_affiliation_strings":["Apple Inc.,USA","Apple Inc., USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc.,USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc., USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842894","display_name":"Leo Liu","orcid":"https://orcid.org/0009-0008-1720-8533"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leo Liu","raw_affiliation_strings":["Apple Inc.,USA","Apple Inc., USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc.,USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc., USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033446148","display_name":"H. Benjamin Mason","orcid":"https://orcid.org/0000-0003-4279-2854"},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Henry Mason","raw_affiliation_strings":["Apple Inc.,USA","Apple Inc., USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc.,USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc., USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["Apple Inc.,USA","Apple Inc., USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc.,USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc., USA","institution_ids":["https://openalex.org/I4210153776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069329694","display_name":"Daben Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153776","display_name":"Apple (United States)","ror":"https://ror.org/059hsda18","country_code":"US","type":"company","lineage":["https://openalex.org/I4210153776"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daben Liu","raw_affiliation_strings":["Apple Inc.,USA","Apple Inc., USA"],"affiliations":[{"raw_affiliation_string":"Apple Inc.,USA","institution_ids":["https://openalex.org/I4210153776"]},{"raw_affiliation_string":"Apple Inc., USA","institution_ids":["https://openalex.org/I4210153776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011008665"],"corresponding_institution_ids":["https://openalex.org/I4210153776"],"apc_list":null,"apc_paid":null,"fwci":4.1093,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.94898114,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6854","last_page":"6858"},"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":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.765932559967041},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367314696311951},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6078200340270996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5907455086708069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5832432508468628},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.557212233543396},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5560373067855835},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5345780849456787},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49639183282852173},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.46498721837997437},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43455034494400024},{"id":"https://openalex.org/keywords/exponential-growth","display_name":"Exponential growth","score":0.41225260496139526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16556516289710999}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.765932559967041},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367314696311951},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6078200340270996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5907455086708069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5832432508468628},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.557212233543396},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5560373067855835},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5345780849456787},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49639183282852173},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.46498721837997437},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43455034494400024},{"id":"https://openalex.org/C75235859","wikidata":"https://www.wikidata.org/wiki/Q582659","display_name":"Exponential growth","level":2,"score":0.41225260496139526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16556516289710999},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W1553004968","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1932847118","https://openalex.org/W2010291496","https://openalex.org/W2097117768","https://openalex.org/W2131342762","https://openalex.org/W2158069733","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2405883473","https://openalex.org/W2588610957","https://openalex.org/W2916979304","https://openalex.org/W2916986993","https://openalex.org/W2962835968","https://openalex.org/W2963300719","https://openalex.org/W2963446712","https://openalex.org/W2963454111","https://openalex.org/W2963490782","https://openalex.org/W2963685250","https://openalex.org/W2964350391","https://openalex.org/W3038058348","https://openalex.org/W6617368339","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6695676441","https://openalex.org/W6733590821","https://openalex.org/W6739879593","https://openalex.org/W6780226713","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W1549363203","https://openalex.org/W4231274751","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W2119113516","https://openalex.org/W4287755480","https://openalex.org/W3113607506","https://openalex.org/W2140435364"],"abstract_inverted_index":{"Very":[0],"deep":[1,25,47],"CNNs":[2,26],"achieve":[3,94],"state-of-the-art":[4],"results":[5],"in":[6,70],"both":[7,83,109],"computer":[8],"vision":[9],"and":[10,58,78,86,111],"speech":[11],"recognition,":[12],"but":[13],"are":[14],"difficult":[15],"to":[16,22,28,90,100,124],"train.":[17],"The":[18],"most":[19],"popular":[20],"way":[21],"train":[23],"very":[24],"is":[27],"use":[29],"shortcut":[30,84],"connections":[31,85],"(SC)":[32],"together":[33],"with":[34,64],"batch":[35,87],"normalization":[36],"(BN).":[37],"Inspired":[38],"by":[39,54,114],"Self-Normalizing":[40],"Neural":[41],"Networks,":[42],"we":[43,92],"propose":[44],"the":[45,56,60,75,80,95],"self-normalizing":[46,77],"CNN":[48],"(SNDCNN)":[49],"based":[50],"acoustic":[51],"model":[52,120],"topology,":[53],"removing":[55],"SC/BN":[57],"replacing":[59],"typical":[61],"RELU":[62],"activations":[63,73],"scaled":[65],"exponential":[66],"linear":[67],"unit":[68],"(SELU)":[69],"ResNet-50.":[71],"SELU":[72],"make":[74],"network":[76],"remove":[79],"need":[81],"for":[82,128],"normalization.":[88],"Compared":[89],"ResNet50,":[91],"can":[93],"same":[96],"or":[97],"lower":[98],"(up":[99],"4.5%":[101],"relative)":[102],"word":[103],"error":[104],"rate":[105],"(WER)":[106],"while":[107],"boosting":[108],"training":[110],"inference":[112,121],"speed":[113],"60%-80%.":[115],"We":[116],"also":[117],"explore":[118],"other":[119],"optimization":[122],"schemes":[123],"further":[125],"reduce":[126],"latency":[127],"production":[129],"use.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}