{"id":"https://openalex.org/W3094855746","doi":"https://doi.org/10.21437/interspeech.2020-1870","title":"A Deep 2D Convolutional Network for Waveform-Based Speech Recognition","display_name":"A Deep 2D Convolutional Network for Waveform-Based Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3094855746","doi":"https://doi.org/10.21437/interspeech.2020-1870","mag":"3094855746"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1870","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/4a397534-58ee-4c62-b503-b762fd7f805c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061934775","display_name":"Dino Ogli\u0107","orcid":"https://orcid.org/0000-0002-4728-9644"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dino Oglic","raw_affiliation_strings":["Department of Engineering, King's College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056805951","display_name":"Zoran Cvetkovi\u0107","orcid":"https://orcid.org/0000-0002-5128-5099"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoran Cvetkovic","raw_affiliation_strings":["Department of Engineering, King's College London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, King's College London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","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":["Center for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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":["Center for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2187,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.84435426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1654","last_page":"1658"},"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":0.9983999729156494,"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":0.7693846225738525},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7109948396682739},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.672101616859436},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5679892301559448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4762416183948517},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4190462827682495},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1040661633014679},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.05155438184738159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693846225738525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7109948396682739},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.672101616859436},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5679892301559448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4762416183948517},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4190462827682495},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1040661633014679},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.05155438184738159}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-1870","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/4a397534-58ee-4c62-b503-b762fd7f805c","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/4a397534-58ee-4c62-b503-b762fd7f805c","pdf_url":"https://www.research.ed.ac.uk/en/publications/4a397534-58ee-4c62-b503-b762fd7f805c","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":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/4a397534-58ee-4c62-b503-b762fd7f805c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/4a397534-58ee-4c62-b503-b762fd7f805c","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":"Oglic, D, Cvetkovic, Z, Bell, P & Renals, S 2020, A Deep 2D Convolutional Network for Waveform-Based Speech Recognition. in Proceedings of Interspeech 2020. International Speech Communication Association, pp. 1654-1658, Interspeech 2020, Virtual Conference, China, 25/10/20. https://doi.org/10.21437/Interspeech.2020-1870","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/4a397534-58ee-4c62-b503-b762fd7f805c","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/4a397534-58ee-4c62-b503-b762fd7f805c","pdf_url":"https://www.research.ed.ac.uk/en/publications/4a397534-58ee-4c62-b503-b762fd7f805c","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":""},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3297227137","display_name":null,"funder_award_id":"EP/R012180/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4304376995","display_name":"SpeechWave","funder_award_id":"EP/R012067/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6167047368","display_name":null,"funder_award_id":"EP/R012067/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3094855746.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W145385712","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1542280630","https://openalex.org/W1994396704","https://openalex.org/W1994906459","https://openalex.org/W1998563636","https://openalex.org/W2087992518","https://openalex.org/W2116217121","https://openalex.org/W2118020555","https://openalex.org/W2131548063","https://openalex.org/W2137295153","https://openalex.org/W2148154194","https://openalex.org/W2154833897","https://openalex.org/W2331927446","https://openalex.org/W2398826216","https://openalex.org/W2402146185","https://openalex.org/W2408093180","https://openalex.org/W2508048623","https://openalex.org/W2514741789","https://openalex.org/W2515753980","https://openalex.org/W2582199702","https://openalex.org/W2766930522","https://openalex.org/W2785397276","https://openalex.org/W2794209590","https://openalex.org/W2799958557","https://openalex.org/W2888909726","https://openalex.org/W2891874693","https://openalex.org/W2903799412","https://openalex.org/W2904818793","https://openalex.org/W2955174253","https://openalex.org/W2962901777","https://openalex.org/W2963071736","https://openalex.org/W2963175699","https://openalex.org/W2963669405","https://openalex.org/W2964227577","https://openalex.org/W2973053574","https://openalex.org/W2979476256","https://openalex.org/W2982427813","https://openalex.org/W2996261834","https://openalex.org/W3006835112","https://openalex.org/W3016042429","https://openalex.org/W4245923654","https://openalex.org/W4298343167","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3009238340","https://openalex.org/W2939353110","https://openalex.org/W3133861977","https://openalex.org/W4321369474","https://openalex.org/W4360585206"],"abstract_inverted_index":{"Due":[0],"to":[1],"limited":[2],"computational":[3],"resources,":[4],"acoustic":[5],"models":[6,164],"of":[7,29,35,51,61,79,100,109,124],"early":[8],"automatic":[9,36],"speech":[10,39,171],"recognition":[11,40],"(":[12],"asr)":[13],"systems":[14],"were":[15],"built":[16],"in":[17,72,90,119],"low-dimensional":[18],"feature":[19],"spaces":[20],"that":[21,42,56,143,157,185],"incur":[22],"considerable":[23],"information":[24,44],"loss":[25,45],"at":[26],"the":[27,30,49,73,80,117,158,189],"outset":[28],"process.":[31],"Several":[32],"comparative":[33],"studies":[34],"and":[37,57,168,173],"human":[38],"suggest":[41],"this":[43,180],"can":[46],"adversely":[47],"affect":[48],"robustness":[50],"asr":[52],"systems.":[53],"To":[54],"mitigate":[55],"allow":[58],"for":[59],"learning":[60,186,197],"robust":[62],"models,":[63],"we":[64],"propose":[65],"a":[66,91,101,130,139],"deep":[67],"2":[68,131,151],"d":[69,132,152],"convolutional":[70,103,133],"network":[71,81],"waveform":[74,118,190],"domain.":[75],"The":[76,113],"first":[77],"layer":[78,115],"decomposes":[82],"waveforms":[83],"into":[84],"frequency":[85],"sub-bands,":[86],"thereby":[87],"representing":[88],"them":[89],"structured":[92],"high-dimensional":[93],"space.":[94],"This":[95,135],"is":[96,136],"achieved":[97],"by":[98,138],"means":[99],"parametric":[102],"block":[104],"defined":[105],"via":[106,129],"cosine":[107],"modulations":[108],"compactly":[110],"supported":[111],"windows.":[112],"next":[114],"embeds":[116],"an":[120],"even":[121],"higher-dimensional":[122],"space":[123],"high-resolution":[125],"spectro-temporal":[126,147],"patterns,":[127],"implemented":[128],"block.":[134],"followed":[137],"gradual":[140],"compression":[141],"phase":[142],"selects":[144],"most":[145],"relevant":[146],"patterns":[148],"using":[149,198],"wide-pass":[150],"filtering.":[153],"Our":[154],"results":[155],"show":[156],"approach":[159],"significantly":[160],"outperforms":[161],"alternative":[162],"waveform-based":[163],"on":[165],"both":[166],"noisy":[167],"spontaneous":[169],"conversational":[170],"(24%":[172],"11%":[174],"relative":[175],"error":[176],"reduction,":[177],"respectively).":[178],"Moreover,":[179],"study":[181],"provides":[182],"empirical":[183],"evidence":[184],"directly":[187],"from":[188],"domain":[191],"could":[192],"be":[193],"more":[194],"effective":[195],"than":[196],"hand-crafted":[199],"features.":[200]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}