{"id":"https://openalex.org/W3095947083","doi":"https://doi.org/10.21437/interspeech.2020-2656","title":"Deep Scattering Power Spectrum Features for Robust Speech Recognition","display_name":"Deep Scattering Power Spectrum Features for Robust Speech Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3095947083","doi":"https://doi.org/10.21437/interspeech.2020-2656","mag":"3095947083"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2656","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2656","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/32443137-57f7-4cf5-9449-44a2757fa955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074777875","display_name":"Neethu Mariam Joy","orcid":"https://orcid.org/0000-0003-2460-5189"},"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":"Neethu M. Joy","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/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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7604,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71810592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1673","last_page":"1677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9902999997138977,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9902999997138977,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9871000051498413,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9369000196456909,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6591939330101013},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5876045823097229},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.4703662097454071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40234190225601196},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11927241086959839}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6591939330101013},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5876045823097229},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.4703662097454071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40234190225601196},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11927241086959839}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2020-2656","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2656","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:openaire/32443137-57f7-4cf5-9449-44a2757fa955","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/32443137-57f7-4cf5-9449-44a2757fa955","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":"Joy, N M, Oglic, D, Cvetkovic, Z, Bell, P & Renals, S 2020, Deep Scattering Power Spectrum Features for Robust Speech Recognition. in Proceedings of Interspeech 2020. International Speech Communication Association, pp. 1673-1677, Interspeech 2020, Virtual Conference, China, 25/10/20. https://doi.org/10.21437/Interspeech.2020-2656","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/32443137-57f7-4cf5-9449-44a2757fa955","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/32443137-57f7-4cf5-9449-44a2757fa955","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/32443137-57f7-4cf5-9449-44a2757fa955","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/32443137-57f7-4cf5-9449-44a2757fa955","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":"Joy, N M, Oglic, D, Cvetkovic, Z, Bell, P & Renals, S 2020, Deep Scattering Power Spectrum Features for Robust Speech Recognition. in Proceedings of Interspeech 2020. International Speech Communication Association, pp. 1673-1677, Interspeech 2020, Virtual Conference, China, 25/10/20. https://doi.org/10.21437/Interspeech.2020-2656","raw_type":"contributionToPeriodical"},"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":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1576701673","https://openalex.org/W1836465849","https://openalex.org/W1904365287","https://openalex.org/W1994906459","https://openalex.org/W2047769394","https://openalex.org/W2069976350","https://openalex.org/W2078279533","https://openalex.org/W2089624763","https://openalex.org/W2093231248","https://openalex.org/W2116217121","https://openalex.org/W2131548063","https://openalex.org/W2154833897","https://openalex.org/W2294139527","https://openalex.org/W2404450935","https://openalex.org/W2515753980","https://openalex.org/W3016042429","https://openalex.org/W4245923654","https://openalex.org/W4302613435","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"Deep":[0],"scattering":[1,70,102,135],"spectrum":[2,137],"consists":[3],"of":[4,7,16,44,56,79,101,109,120],"a":[5,65],"cascade":[6],"wavelet":[8],"transforms":[9],"and":[10,30,116,145,181,192],"modulus":[11,81,95],"non-linearity.":[12,96],"It":[13],"generates":[14],"features":[15,103,187],"different":[17,124],"orders,":[18],"with":[19,87,123],"the":[20,27,42,46,54,68,80,93,99,105,132,177,184],"first":[21,185],"order":[22,32,51,134,179,186],"coefficients":[23,33,52,89,138],"approximately":[24],"equal":[25],"to":[26,67,85,152],"Mel-frequency":[28],"cepstrum,":[29],"higher":[31,50],"recovering":[34],"information":[35,47,149,180],"lost":[36],"at":[37],"lower":[38],"levels.":[39],"We":[40,97],"investigate":[41],"effect":[43],"including":[45],"recovered":[48],"by":[49],"on":[53,113,161,170],"robustness":[55,100,144],"speech":[57,115,171],"recognition.":[58],"To":[59],"that":[60,131,146,174],"end,":[61],"we":[62,83],"also":[63],"propose":[64],"modification":[66],"original":[69],"transform":[71],"tailored":[72],"for":[73,142,189],"noisy":[74],"speech.":[75,197],"In":[76],"particular,":[77],"instead":[78],"non-linearity":[82],"opt":[84],"work":[86],"power":[88,136],"and,":[90],"therefore,":[91],"use":[92],"squared":[94],"quantify":[98],"using":[104,118],"word":[106],"error":[107,159],"rates":[108],"acoustic":[110],"models":[111],"trained":[112],"clean":[114],"evaluated":[117],"sets":[119],"utterances":[121],"corrupted":[122],"noise":[125,143,154],"types.":[126],"Our":[127],"empirical":[128],"results":[129],"show":[130],"second":[133,178],"capture":[139],"invariants":[140],"relevant":[141],"this":[147],"additional":[148],"improves":[150],"generalization":[151],"unseen":[153],"conditions":[155],"(almost":[156],"20%":[157],"relative":[158],"reduction":[160],"aurora":[162],"4).":[163],"This":[164],"finding":[165],"can":[166],"have":[167],"important":[168],"consequences":[169],"recognition":[172],"systems":[173],"typically":[175],"discard":[176],"keep":[182],"only":[183],"(known":[188],"emulating":[190],"mfcc":[191],"fbank":[193],"values)":[194],"when":[195],"representing":[196]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}