{"id":"https://openalex.org/W1969851134","doi":"https://doi.org/10.1109/asru.2013.6707746","title":"Learning filter banks within a deep neural network framework","display_name":"Learning filter banks within a deep neural network framework","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1969851134","doi":"https://doi.org/10.1109/asru.2013.6707746","mag":"1969851134"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Tara N. Sainath","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Brian Kingsbury","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103742478","display_name":"Abdelrahman Mohamed","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdel-rahman Mohamed","raw_affiliation_strings":["Department of Computer Science, University of Toronto, Canada","DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"DEPARTMENT OF COMPUTER SCIENCE, UNIVERSITY OF TORONTO, TORONTO, ON, CANADA","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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","IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights , NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"297","last_page":"302"},"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":0.9998999834060669,"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":0.9994999766349792,"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/filter-bank","display_name":"Filter bank","score":0.8460317850112915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073565125465393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6719670295715332},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.620635986328125},{"id":"https://openalex.org/keywords/filter-design","display_name":"Filter design","score":0.525327205657959},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46039479970932007},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.429696261882782},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.13794755935668945}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8460317850112915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073565125465393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6719670295715332},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.620635986328125},{"id":"https://openalex.org/C22597639","wikidata":"https://www.wikidata.org/wiki/Q5449227","display_name":"Filter design","level":3,"score":0.525327205657959},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46039479970932007},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.429696261882782},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.13794755935668945}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W16408605","https://openalex.org/W21805524","https://openalex.org/W59592858","https://openalex.org/W104211377","https://openalex.org/W1498436455","https://openalex.org/W1538131130","https://openalex.org/W1904365287","https://openalex.org/W2036242736","https://openalex.org/W2076794394","https://openalex.org/W2106119541","https://openalex.org/W2112739286","https://openalex.org/W2114016253","https://openalex.org/W2118595744","https://openalex.org/W2133246939","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2155117693","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2914484425","https://openalex.org/W4238404964","https://openalex.org/W6600886765","https://openalex.org/W6602426124","https://openalex.org/W6604310120","https://openalex.org/W6629815555","https://openalex.org/W6632100814","https://openalex.org/W6640036494"],"related_works":["https://openalex.org/W1551719041","https://openalex.org/W2118799423","https://openalex.org/W997673828","https://openalex.org/W2144405339","https://openalex.org/W2118299246","https://openalex.org/W2096998134","https://openalex.org/W2575993598","https://openalex.org/W2161811162","https://openalex.org/W2184136511","https://openalex.org/W2390004645"],"abstract_inverted_index":{"Mel-filter":[0],"banks":[1,25],"are":[2,10,26],"commonly":[3],"used":[4],"in":[5,116],"speech":[6,16,52,96],"recognition,":[7],"as":[8,41],"they":[9],"motivated":[11],"from":[12,23],"theory":[13],"related":[14],"to":[15,86,94,128],"production":[17],"and":[18],"perception.":[19],"While":[20],"features":[21],"derived":[22],"mel-filter":[24],"quite":[27],"popular,":[28],"we":[29,57,106,109],"argue":[30],"that":[31,68,108],"this":[32,55],"filter":[33,61,65,82,123],"bank":[34,62,66,83,124],"is":[35,43,69,84,90],"not":[36,44],"really":[37],"an":[38],"appropriate":[39],"choice":[40],"it":[42],"learned":[45,70,85],"for":[46],"the":[47,60,73,81,95,122],"objective":[48],"at":[49],"hand,":[50],"i.e.":[51],"recognition.":[53],"In":[54],"paper,":[56],"explore":[58],"replacing":[59],"with":[63,72],"a":[64,76,100,112,130],"layer":[67],"jointly":[71],"rest":[74],"of":[75,133],"deep":[77],"neural":[78],"network.":[79],"Thus,":[80],"minimize":[87],"cross-entropy,":[88],"which":[89],"more":[91],"closely":[92],"tied":[93],"recognition":[97],"objective.":[98],"On":[99],"50-hour":[101],"English":[102],"Broadcast":[103],"News":[104],"task,":[105],"show":[107],"can":[110],"achieve":[111],"5%":[113],"relative":[114],"improvement":[115],"word":[117],"error":[118],"rate":[119],"(WER)":[120],"using":[121],"learning":[125],"approach,":[126],"compared":[127],"having":[129],"fixed":[131],"set":[132],"filters.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":12}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}