{"id":"https://openalex.org/W2982427813","doi":"https://doi.org/10.1109/icassp40776.2020.9053703","title":"Multi-Scale Octave Convolutions for Robust Speech Recognition","display_name":"Multi-Scale Octave Convolutions for Robust Speech Recognition","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982427813","doi":"https://doi.org/10.1109/icassp40776.2020.9053703","mag":"2982427813"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053703","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.14443","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":true,"raw_author_name":"Joanna Rownicka","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, UK","[University of Edinburgh,Centre for Speech Technology Research,UK]"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[University of Edinburgh,Centre for Speech Technology Research,UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["Centre for Speech Technology Research, University of Edinburgh, UK","[University of Edinburgh,Centre for Speech Technology Research,UK]"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[University of Edinburgh,Centre for Speech Technology Research,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, University of Edinburgh, UK","[University of Edinburgh,Centre for Speech Technology Research,UK]"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[University of Edinburgh,Centre for Speech Technology Research,UK]","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026578899"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.73429774,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74689596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7019","last_page":"7023"},"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":0.9997000098228455,"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":0.9993000030517578,"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/octave","display_name":"Octave (electronics)","score":0.7418904900550842},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6901664733886719},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6824615001678467},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5574823021888733},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4333884119987488},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4034295976161957},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13208267092704773}],"concepts":[{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.7418904900550842},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6901664733886719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6824615001678467},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5574823021888733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4333884119987488},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4034295976161957},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13208267092704773},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053703","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053703","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"},{"id":"pmh:oai:arXiv.org:1910.14443","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14443","pdf_url":"https://arxiv.org/pdf/1910.14443","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2982427813","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1910.14443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:pure.ed.ac.uk:openaire/8ad253c6-cd82-442d-ab55-74c5e2709e1a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8ad253c6-cd82-442d-ab55-74c5e2709e1a","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"R\u00f3wnicka, J, Bell, P & Renals, S 2020, Multi-Scale Octave Convolutions for Robust Speech Recognition. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 7019-7023, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053703","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/8ad253c6-cd82-442d-ab55-74c5e2709e1a","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/9053703","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"R\u00f3wnicka, J, Bell, P & Renals, S 2020, Multi-Scale Octave Convolutions for Robust Speech Recognition. in ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 7019-7023, 2020 IEEE International Conference on Acoustics, Speech, and Signal Processing, Barcelona, Spain, 4/05/20. https://doi.org/10.1109/ICASSP40776.2020.9053703","raw_type":"contributionToPeriodical"},{"id":"doi:10.48550/arxiv.1910.14443","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.14443","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/h903-vj10","is_oa":true,"landing_page_url":"https://doi.org/10.17023/h903-vj10","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.14443","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.14443","pdf_url":"https://arxiv.org/pdf/1910.14443","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2108442954","https://openalex.org/W2148613904","https://openalex.org/W2153773386","https://openalex.org/W2198724430","https://openalex.org/W2395510410","https://openalex.org/W2515863432","https://openalex.org/W2587717635","https://openalex.org/W2616139854","https://openalex.org/W2739959771","https://openalex.org/W2786152338","https://openalex.org/W2797187289","https://openalex.org/W2883111419","https://openalex.org/W2883780447","https://openalex.org/W2955174253","https://openalex.org/W2955425717","https://openalex.org/W2962835968","https://openalex.org/W2962965870","https://openalex.org/W2963174142","https://openalex.org/W2963241429","https://openalex.org/W2963993763","https://openalex.org/W2988396473","https://openalex.org/W6637373629","https://openalex.org/W6726275242","https://openalex.org/W6746586578","https://openalex.org/W6753767121","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W3016042429","https://openalex.org/W2904818793","https://openalex.org/W2903799412","https://openalex.org/W2515753980","https://openalex.org/W2118020555","https://openalex.org/W2116217121","https://openalex.org/W1524333225","https://openalex.org/W2292414329","https://openalex.org/W3100453183","https://openalex.org/W2282761944","https://openalex.org/W154459060","https://openalex.org/W3128223806","https://openalex.org/W2104485902","https://openalex.org/W2302205572","https://openalex.org/W2799958557","https://openalex.org/W3125868443","https://openalex.org/W2401055552","https://openalex.org/W2787870360","https://openalex.org/W2939776061","https://openalex.org/W2911786100"],"abstract_inverted_index":{"We":[0,86,115,130],"propose":[1],"a":[2,41,112,166],"multi-scale":[3],"octave":[4,53,89,133],"convolution":[5,134],"layer":[6,43],"to":[7,27,74,99,136,181],"learn":[8],"robust":[9],"speech":[10,124],"representations":[11,97],"efficiently.":[12],"Octave":[13],"convolutions":[14,90],"were":[15],"introduced":[16],"by":[17,36,119,179],"Chen":[18],"et":[19],"al":[20],"[1]":[21],"in":[22,81,105],"the":[23,29,33,38,58,63,66,75,78,82,93,100,106,132,145,148,153,177,192,196],"computer":[24],"vision":[25],"field":[26,80],"reduce":[28],"spatial":[30,50],"redundancy":[31],"of":[32,40,65,77,95,102,147,195],"feature":[34,45],"maps":[35,46],"decomposing":[37],"output":[39],"convolutional":[42],"into":[44],"at":[47],"two":[48,122],"different":[49],"resolutions,":[51],"one":[52],"apart.":[54],"This":[55],"approach":[56],"improved":[57],"efficiency":[59,194],"as":[60,62,111,165],"well":[61],"accuracy":[64,70],"CNN":[67,197],"models.":[68,199],"The":[69,170],"gain":[71],"was":[72],"attributed":[73],"enlargement":[76],"receptive":[79],"original":[83],"input":[84],"space.":[85],"argue":[87],"that":[88,173],"likewise":[91],"improve":[92],"robustness":[94,146,168],"learned":[96],"due":[98],"use":[101],"average":[103],"pooling":[104],"lower":[107],"resolution":[108,138],"group,":[109],"acting":[110],"low-pass":[113],"filter.":[114],"test":[116],"this":[117],"hypothesis":[118],"evaluating":[120],"on":[121],"noisy":[123,158],"corpora":[125],"-":[126],"Aurora-4":[127,185],"and":[128,140,157,186],"AMI.":[129],"extend":[131],"concept":[135],"multiple":[137,141],"groups":[139],"octaves.":[142],"To":[143],"evaluate":[144],"inferred":[149],"representations,":[150],"we":[151],"report":[152],"similarity":[154],"between":[155],"clean":[156],"encodings":[159],"using":[160],"an":[161],"affine":[162],"projection":[163],"loss":[164],"proxy":[167],"measure.":[169],"results":[171],"show":[172],"proposed":[174],"method":[175],"reduces":[176],"WER":[178],"up":[180],"6.6%":[182],"relative":[183],"for":[184,188],"3.6%":[187],"AMI,":[189],"while":[190],"improving":[191],"computational":[193],"acoustic":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}