{"id":"https://openalex.org/W4236328885","doi":"https://doi.org/10.21437/interspeech.2020-17","title":"On the Robustness and Training Dynamics of Raw Waveform Models","display_name":"On the Robustness and Training Dynamics of Raw Waveform Models","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W4236328885","doi":"https://doi.org/10.21437/interspeech.2020-17"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-17","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":"conference-paper","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/A5042184515","display_name":"Erfan Loweimi","orcid":"https://orcid.org/0000-0002-8761-021X"},"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":"Erfan Loweimi","raw_affiliation_strings":["Centre for Speech Technology Research (CSTR), The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), The University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081337679","display_name":"Peter Bell","orcid":"https://orcid.org/0000-0003-4415-7408"},"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":["Centre for Speech Technology Research (CSTR), The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), The University of Edinburgh, 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":["Centre for Speech Technology Research (CSTR), The University of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research (CSTR), The University of Edinburgh, Edinburgh, UK","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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1001","last_page":"1005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8184000253677368,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.8184000253677368,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7315999865531921,"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/T11801","display_name":"Reservoir Engineering and Simulation Methods","score":0.7269999980926514,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8171036243438721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6902161836624146},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6431323289871216},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4416589140892029},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08906546235084534},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.056055307388305664},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.055983513593673706}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8171036243438721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902161836624146},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6431323289871216},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4416589140892029},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08906546235084534},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.056055307388305664},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.055983513593673706},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-17","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:repository@napier.ac.uk:3585868","is_oa":false,"landing_page_url":"http://researchrepository.napier.ac.uk/Output/3585868","pdf_url":null,"source":{"id":"https://openalex.org/S4306402591","display_name":"Edinburgh Napier Research Repository (Edinburgh Napier University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I251738","host_organization_name":"Edinburgh Napier University","host_organization_lineage":["https://openalex.org/I251738"],"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":"Presentation / Conference Contribution"}],"best_oa_location":null,"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"}],"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":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1519757598","https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1600744878","https://openalex.org/W1666984270","https://openalex.org/W1836465849","https://openalex.org/W2090861223","https://openalex.org/W2095705004","https://openalex.org/W2105059898","https://openalex.org/W2119125873","https://openalex.org/W2132037657","https://openalex.org/W2151484683","https://openalex.org/W2151796392","https://openalex.org/W2156387975","https://openalex.org/W2168249605","https://openalex.org/W2398826216","https://openalex.org/W2401447047","https://openalex.org/W2401869809","https://openalex.org/W2404126548","https://openalex.org/W2408093180","https://openalex.org/W2508048623","https://openalex.org/W2539406037","https://openalex.org/W2746321128","https://openalex.org/W2799958557","https://openalex.org/W2805215415","https://openalex.org/W2899771611","https://openalex.org/W2938255784","https://openalex.org/W2955174253","https://openalex.org/W2963175699","https://openalex.org/W2963669405","https://openalex.org/W2964227577","https://openalex.org/W2973053574","https://openalex.org/W3006835112","https://openalex.org/W3007948068","https://openalex.org/W3015579786","https://openalex.org/W4245923654","https://openalex.org/W4297970144","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W4367555392","https://openalex.org/W2374664672","https://openalex.org/W2056136368"],"abstract_inverted_index":{"We":[0,88],"investigate":[1,68],"the":[2,21,53,69,73,78,91,106,109,115,118,132],"robustness":[3,133],"and":[4,64,105,123,141,164,181],"training":[5,70],"dynamics":[6,71,107,116],"of":[7,24,30,35,59,72,80,98,108,117,134,146,174],"raw":[8,135,175],"waveform":[9,136,176],"acoustic":[10],"models":[11,26,137,148],"for":[12],"automatic":[13],"speech":[14],"recognition":[15],"(ASR).":[16],"It":[17],"is":[18,40,149],"known":[19],"that":[20,90],"first":[22,74,110],"layer":[23,39,75,111],"such":[25],"learn":[27],"a":[28,33,57,101,169],"set":[29,58,97],"filters,":[31],"performing":[32],"form":[34],"time-frequency":[36],"analysis.":[37],"This":[38],"liable":[41],"to":[42,46,151,183],"be":[43,152],"under-trained":[44],"owing":[45],"gradient":[47],"vanishing,":[48],"which":[49],"can":[50],"negatively":[51],"affect":[52],"network":[54,92],"performance.":[55],"Through":[56],"experiments":[60],"on":[61],"TIMIT,":[62],"Aurora-4":[63],"WSJ":[65],"datasets,":[66],"we":[67,130],"by":[76,167],"measuring":[77],"evolution":[79],"its":[81],"average":[82],"frequency":[83],"response":[84],"over":[85],"different":[86],"epochs.":[87],"demonstrate":[89],"efficiently":[93],"learns":[94],"an":[95],"optimal":[96],"filters":[99],"with":[100,114],"high":[102],"spectral":[103],"resolution":[104],"highly":[112],"correlates":[113],"cross":[119],"entropy":[120],"(CE)":[121],"loss":[122],"word":[124],"error":[125],"rate":[126],"(WER).":[127],"In":[128],"addition,":[129],"study":[131],"in":[138,161,188],"both":[139],"matched":[140,162],"mismatched":[142,189],"conditions.":[143],"The":[144,172],"accuracy":[145],"these":[147],"found":[150],"comparable":[153],"to,":[154],"or":[155],"better":[156,170],"than,":[157],"their":[158],"MFCC-based":[159],"counterparts":[160],"conditions":[163,190],"notably":[165],"improved":[166],"using":[168],"alignment.":[171],"role":[173],"normalisation":[177],"was":[178,191],"also":[179],"examined":[180],"up":[182],"4.3%":[184],"absolute":[185],"WER":[186],"reduction":[187],"achieved.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}