{"id":"https://openalex.org/W2006577961","doi":"https://doi.org/10.1109/icassp.2014.6854925","title":"Improvements to filterbank and delta learning within a deep neural network framework","display_name":"Improvements to filterbank and delta learning within a deep neural network framework","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2006577961","doi":"https://doi.org/10.1109/icassp.2014.6854925","mag":"2006577961"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854925","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/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":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"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":"George Saon","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":"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6839","last_page":"6843"},"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":0.9998000264167786,"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":0.9991999864578247,"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":0.7719271183013916},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.702752411365509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6887336373329163},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6353161334991455},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5838481187820435},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5468373894691467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5296682715415955},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5198988914489746},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11732518672943115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7719271183013916},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.702752411365509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6887336373329163},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6353161334991455},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5838481187820435},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5468373894691467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5296682715415955},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5198988914489746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11732518672943115}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854925","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":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W21805524","https://openalex.org/W154677192","https://openalex.org/W1498436455","https://openalex.org/W1616590059","https://openalex.org/W1969851134","https://openalex.org/W2002342963","https://openalex.org/W2028706510","https://openalex.org/W2079623482","https://openalex.org/W2096051479","https://openalex.org/W2106119541","https://openalex.org/W2112739286","https://openalex.org/W2114016253","https://openalex.org/W2118595744","https://openalex.org/W2125234026","https://openalex.org/W2137075158","https://openalex.org/W2148154194","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2172097686","https://openalex.org/W2184045248","https://openalex.org/W2962719052","https://openalex.org/W4312531999","https://openalex.org/W6600886765"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Many":[0],"features":[1],"used":[2],"in":[3,107,145],"speech":[4],"recognition":[5],"tasks":[6],"are":[7,10],"hand-crafted":[8],"and":[9,86,115,126,136],"not":[11],"always":[12],"related":[13],"to":[14,61,119,148],"the":[15,45,72,113],"objective":[16],"at":[17],"hand,":[18],"that":[19,28,40,99,134],"is":[20,41],"minimizing":[21],"word":[22,108],"error":[23,109],"rate.":[24],"Recently,":[25],"we":[26,57,67,77,97,100,132],"showed":[27],"replacing":[29],"a":[30,36,48,62,91,103,121,141,149],"perceptually":[31],"motivated":[32],"mel-filter":[33],"bank":[34,38],"with":[35,44],"filter":[37,59,73,114,135],"layer":[39],"learned":[42],"jointly":[43],"rest":[46],"of":[47,124],"deep":[49],"neural":[50],"network":[51],"was":[52],"promising.":[53],"In":[54],"this":[55],"paper,":[56],"extend":[58],"learning":[60,70,74,138],"speaker-adapted,":[63],"state-of-the-art":[64,150],"system.":[65],"First,":[66],"incorporate":[68,78],"delta":[69,116,137],"into":[71],"framework.":[75],"Second,":[76],"various":[79],"speaker":[80,87,130],"adaptation":[81],"techniques,":[82],"including":[83],"VTLN":[84],"warping":[85],"identity":[88],"features.":[89],"On":[90],"50-hour":[92],"English":[93],"Broadcast":[94],"News":[95],"task,":[96],"show":[98],"can":[101],"achieve":[102],"5%":[104],"relative":[105,143],"improvement":[106,144],"rate":[110],"(WER)":[111],"using":[112],"learning,":[117],"compared":[118,147],"having":[120],"fixed":[122],"set":[123],"filters":[125],"deltas.":[127],"Furthermore,":[128],"after":[129],"adaptation,":[131],"find":[133],"allows":[139],"for":[140],"3%":[142],"WER":[146],"CNN.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}