{"id":"https://openalex.org/W2786152338","doi":"https://doi.org/10.1109/asru.2017.8268941","title":"Simplifying very deep convolutional neural network architectures for robust speech recognition","display_name":"Simplifying very deep convolutional neural network architectures for robust speech recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786152338","doi":"https://doi.org/10.1109/asru.2017.8268941","mag":"2786152338"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268941","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/c223dc6b-9917-4f2f-a590-ad2c5d2e3412","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026578899","display_name":"Joanna Rownicka","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joanna Rownicka","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102911387","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0002-9597-9615"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Bell","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"64","issue":null,"first_page":"236","last_page":"243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.9973999857902527,"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":0.8276358842849731},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8238295912742615},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7283273339271545},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6403905749320984},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5945765376091003},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5457664132118225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5383888483047485},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49253568053245544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48674917221069336},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4757658839225769},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47175389528274536},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41301512718200684},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37046223878860474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276358842849731},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8238295912742615},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7283273339271545},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6403905749320984},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5945765376091003},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5457664132118225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5383888483047485},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49253568053245544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48674917221069336},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4757658839225769},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47175389528274536},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41301512718200684},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37046223878860474},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2017.8268941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268941","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/c223dc6b-9917-4f2f-a590-ad2c5d2e3412","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c223dc6b-9917-4f2f-a590-ad2c5d2e3412","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rownicka, J, Renals, S & Bell, P 2018, Simplifying very deep convolutional neural network architectures for robust speech recognition. in IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2017). Institute of Electrical and Electronics Engineers, pp. 236-243, 2017 IEEE Automatic Speech Recognition and Understanding Workshop , Okinawa, Japan, 16/12/17. https://doi.org/10.1109/ASRU.2017.8268941","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/c223dc6b-9917-4f2f-a590-ad2c5d2e3412","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/simplifying-very-deep-convolutional-neural-network-architectures-for-robust-speech-recognition(c223dc6b-9917-4f2f-a590-ad2c5d2e3412).html","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/c223dc6b-9917-4f2f-a590-ad2c5d2e3412","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/c223dc6b-9917-4f2f-a590-ad2c5d2e3412","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Rownicka, J, Renals, S & Bell, P 2018, Simplifying very deep convolutional neural network architectures for robust speech recognition. in IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2017). Institute of Electrical and Electronics Engineers, pp. 236-243, 2017 IEEE Automatic Speech Recognition and Understanding Workshop , Okinawa, Japan, 16/12/17. https://doi.org/10.1109/ASRU.2017.8268941","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1555696814","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1995562189","https://openalex.org/W2033310064","https://openalex.org/W2048060899","https://openalex.org/W2097117768","https://openalex.org/W2103088716","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2123045220","https://openalex.org/W2154579312","https://openalex.org/W2162741153","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2288371874","https://openalex.org/W2402146185","https://openalex.org/W2515753980","https://openalex.org/W2515863432","https://openalex.org/W2587717635","https://openalex.org/W2962719052","https://openalex.org/W2963174142","https://openalex.org/W2963382180","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6677995690","https://openalex.org/W6682751323","https://openalex.org/W6684191040","https://openalex.org/W6712930963","https://openalex.org/W6733140621"],"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":{"Very":[0],"deep":[1],"convolutional":[2,88],"neural":[3],"networks":[4],"(VDCNNs)":[5],"have":[6,16,47,67,116],"been":[7,17],"successfully":[8],"used":[9,111],"in":[10,39,112],"computer":[11,26],"vision.":[12,27],"More":[13],"recently":[14],"VDCNNs":[15,147],"applied":[18],"to":[19,71,106,121],"speech":[20,44,113],"recognition,":[21],"using":[22,129],"architectures":[23,41,109],"adopted":[24],"from":[25],"In":[28],"this":[29,149],"paper,":[30],"we":[31],"experimentally":[32],"analyse":[33],"the":[34,37,58,122,138,142],"role":[35],"of":[36,51,60,87,125],"components":[38],"VDCNN":[40,53,108],"for":[42],"robust":[43],"recognition.":[45,114],"We":[46,66,115],"proposed":[48,83],"a":[49,97],"number":[50],"simplified":[52],"architectures,":[54],"taking":[55],"into":[56],"account":[57],"use":[59],"fully-connected":[61,94],"layers":[62],"and":[63,77,91],"down-sampling":[64],"approaches.":[65],"investigated":[68],"three":[69],"ways":[70],"down-sample":[72],"feature":[73],"maps:":[74],"max-pooling,":[75],"average-pooling,":[76],"convolution":[78],"with":[79],"increased":[80],"stride.":[81],"Our":[82],"model":[84],"consisting":[85],"solely":[86],"(conv)":[89],"layers,":[90,95],"without":[92],"any":[93],"achieves":[96,141],"lower":[98],"word":[99],"error":[100],"rate":[101],"on":[102,148],"Aurora":[103],"4":[104],"compared":[105],"other":[107],"typically":[110],"also":[117],"extended":[118],"our":[119,146],"experiments":[120],"MGB-3":[123,134],"task":[124,150],"multi-genre":[126],"broadcast":[127],"recognition":[128],"BBC":[130],"TV":[131],"recordings.":[132],"The":[133],"results":[135],"indicate":[136],"that":[137],"same":[139],"architecture":[140],"best":[143],"result":[144],"among":[145],"as":[151],"well.":[152]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}