{"id":"https://openalex.org/W2515863432","doi":"https://doi.org/10.21437/interspeech.2016-251","title":"Deep Convolutional Neural Networks with Layer-Wise Context Expansion and Attention","display_name":"Deep Convolutional Neural Networks with Layer-Wise Context Expansion and Attention","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2515863432","doi":"https://doi.org/10.21437/interspeech.2016-251","mag":"2515863432"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-251","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","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/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020361","display_name":"Wayne Xiong","orcid":"https://orcid.org/0000-0003-2854-1143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wayne Xiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Stolcke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062476869","display_name":"Guoli Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoli Ye","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["(Microsoft)"],"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5034476404"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.5667,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.99320753,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"17","last_page":"21"},"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":0.9983999729156494,"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":0.7411984801292419},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7035906314849854},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5730452537536621},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5574601888656616},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4917509853839874},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4210377335548401},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.11511304974555969},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07438716292381287},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.05175366997718811}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7411984801292419},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7035906314849854},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5730452537536621},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5574601888656616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4917509853839874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4210377335548401},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.11511304974555969},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07438716292381287},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.05175366997718811},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2016-251","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"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":33,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W854541894","https://openalex.org/W1538131130","https://openalex.org/W1554982972","https://openalex.org/W1555696814","https://openalex.org/W1557160870","https://openalex.org/W1569189596","https://openalex.org/W1600744878","https://openalex.org/W1666984270","https://openalex.org/W1995562189","https://openalex.org/W2103088716","https://openalex.org/W2112739286","https://openalex.org/W2147768505","https://openalex.org/W2155273149","https://openalex.org/W2181607856","https://openalex.org/W2188183693","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2208299922","https://openalex.org/W2288217446","https://openalex.org/W2292414329","https://openalex.org/W2394932179","https://openalex.org/W2397947827","https://openalex.org/W2398187210","https://openalex.org/W2398319612","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2402146185","https://openalex.org/W2407022425","https://openalex.org/W2514741789","https://openalex.org/W2964084166","https://openalex.org/W2964308564"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W4200173597","https://openalex.org/W3116150086","https://openalex.org/W2999805992","https://openalex.org/W4291897433","https://openalex.org/W3011074480","https://openalex.org/W3192840557"],"abstract_inverted_index":{"In":[0,23],"this":[1,71],"paper,":[2],"we":[3],"propose":[4],"a":[5],"deep":[6],"convolutional":[7],"neural":[8],"network":[9],"(CNN)":[10],"with":[11],"layer-wise":[12,51],"context":[13,52],"expansion":[14,53],"and":[15,38,54,66,91,106],"location-based":[16,56],"attention,":[17],"for":[18],"large":[19],"vocabulary":[20],"speech":[21],"recognition.":[22],"our":[24,83,100],"model":[25,101],"each":[26],"higher":[27],"layer":[28],"uses":[29],"information":[30],"from":[31],"broader":[32],"contexts,":[33],"along":[34],"both":[35,49,103],"the":[36,50,55,62,67,87,92,104],"time":[37],"frequency":[39],"dimensions,":[40],"than":[41],"its":[42],"immediate":[43],"lower":[44],"layer.":[45],"We":[46],"show":[47],"that":[48,99],"attention":[57],"can":[58],"be":[59],"implemented":[60],"using":[61],"element-wise":[63],"matrix":[64],"product":[65],"convolution":[68],"operation.":[69],"For":[70],"reason,":[72],"contrary":[73],"to":[74],"other":[75],"CNNs,":[76],"no":[77],"pooling":[78],"operation":[79],"is":[80],"used":[81],"in":[82],"model.":[84],"Experiments":[85],"on":[86],"309hr":[88],"Switchboard":[89],"task":[90,97],"375hr":[93],"short":[94],"message":[95],"dictation":[96],"indicates":[98],"outperforms":[102],"DNN":[105],"LSTM":[107],"significantly.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":23},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-10-10T00:00:00"}