{"id":"https://openalex.org/W2154833897","doi":"https://doi.org/10.1109/icassp.2014.6853588","title":"Deep Scattering Spectrum with deep neural networks","display_name":"Deep Scattering Spectrum with deep neural networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2154833897","doi":"https://doi.org/10.1109/icassp.2014.6853588","mag":"2154833897"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":["Center for Language and Speech processing, Johns Hopkins University, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech processing, Johns Hopkins University, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111970670","display_name":"TaraN. Sainath","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"TaraN. Sainath","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063706676","display_name":"Shay Maymon","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shay Maymon","raw_affiliation_strings":["Center for Language and Speech processing, Johns Hopkins University, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech processing, Johns Hopkins University, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007586881","display_name":"D. Nahamoo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Nahamoo","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034451965","display_name":"Vaibhava Goel","orcid":"https://orcid.org/0000-0002-5504-3863"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhava Goel","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/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/computer-science","display_name":"Computer science","score":0.6785597801208496},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6639153957366943},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6475122570991516},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5527627468109131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.519365131855011},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4682368338108063},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43837404251098633},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.43274006247520447},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42487451434135437},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4169135093688965},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3980897068977356},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3337404727935791},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.1990126073360443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785597801208496},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6639153957366943},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6475122570991516},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5527627468109131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.519365131855011},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4682368338108063},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43837404251098633},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.43274006247520447},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42487451434135437},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4169135093688965},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3980897068977356},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3337404727935791},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.1990126073360443},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853588","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1492459858","https://openalex.org/W1576579425","https://openalex.org/W1665214252","https://openalex.org/W1969851134","https://openalex.org/W1994906459","https://openalex.org/W2028706510","https://openalex.org/W2062227835","https://openalex.org/W2072072671","https://openalex.org/W2088137865","https://openalex.org/W2090861223","https://openalex.org/W2093231248","https://openalex.org/W2101596234","https://openalex.org/W2112739286","https://openalex.org/W2118595744","https://openalex.org/W2129901640","https://openalex.org/W2137075158","https://openalex.org/W2143612262","https://openalex.org/W2147676440","https://openalex.org/W2148154194","https://openalex.org/W2152483743","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2404206164","https://openalex.org/W2914484425","https://openalex.org/W2962719052","https://openalex.org/W2963175699","https://openalex.org/W4238404964","https://openalex.org/W6637242042","https://openalex.org/W6678409544","https://openalex.org/W6713427716"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W1573546415","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973"],"abstract_inverted_index":{"State-of-the-art":[0],"convolutional":[1],"neural":[2,114],"networks":[3],"(CNNs)":[4],"typically":[5],"use":[6,101,127],"a":[7,151],"log-mel":[8,26,65,146],"spectral":[9],"representation":[10,17],"of":[11,54,128,142,156,159],"the":[12,21,51,55,80,86,111,160],"speech":[13],"signal.":[14],"However,":[15],"this":[16,38,167],"is":[18,62],"limited":[19],"by":[20,25],"spectro-temporal":[22],"resolution":[23,43,88],"afforded":[24],"filter-banks.":[27],"A":[28],"novel":[29],"technique":[30],"known":[31],"as":[32],"Deep":[33],"Scattering":[34],"Spectrum":[35],"(DSS)":[36],"addresses":[37],"limitation":[39],"and":[40,67,117],"preserves":[41,85],"higher":[42,81,87,123,130],"information,":[44,89],"while":[45],"ensuring":[46],"time":[47],"warp":[48],"stability,":[49],"through":[50],"cascaded":[52],"application":[53],"wavelet-modulus":[56],"operator.":[57],"The":[58,126],"first":[59],"order":[60,82,124,131],"scatter":[61,132],"equivalent":[63],"to":[64,99,120,145,164],"features":[66,103,147],"standard":[68],"CNN":[69,105],"modeling":[70],"techniques":[71,119],"can":[72],"directly":[73],"be":[74],"used":[75],"with":[76,104,136],"these":[77,129],"features.":[78],"However":[79],"scatter,":[83],"which":[84],"presents":[90],"new":[91],"challenges":[92],"in":[93,134,139],"modelling.":[94],"This":[95],"paper":[96],"explores":[97],"how":[98],"effectively":[100,121],"DSS":[102],"acoustic":[106],"models.":[107],"Specifically,":[108],"we":[109],"identify":[110],"effective":[112],"normalization,":[113],"network":[115],"topology":[116],"regularization":[118],"model":[122],"scatter.":[125],"features,":[133],"conjunction":[135],"CNNs,":[137],"results":[138],"relative":[140],"improvement":[141],"7%":[143],"compared":[144],"on":[148,166],"TIMIT,":[149],"providing":[150],"phonetic":[152],"error":[153],"rate":[154],"(PER)":[155],"17.4%,":[157],"one":[158],"lowest":[161],"reported":[162],"PERs":[163],"date":[165],"task.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}