{"id":"https://openalex.org/W2508627142","doi":"https://doi.org/10.1109/taslp.2016.2607341","title":"Novel Unsupervised Auditory Filterbank Learning Using Convolutional RBM for Speech Recognition","display_name":"Novel Unsupervised Auditory Filterbank Learning Using Convolutional RBM for Speech Recognition","publication_year":2016,"publication_date":"2016-09-08","ids":{"openalex":"https://openalex.org/W2508627142","doi":"https://doi.org/10.1109/taslp.2016.2607341","mag":"2508627142"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2607341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2607341","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik B. Sailor","raw_affiliation_strings":["Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I98389781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043002276","display_name":"Hemant A. Patil","orcid":"https://orcid.org/0000-0002-4068-2005"},"institutions":[{"id":"https://openalex.org/I98389781","display_name":"Dhirubhai Ambani University","ror":"https://ror.org/02d5b7g69","country_code":"IN","type":"education","lineage":["https://openalex.org/I98389781"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hemant A. Patil","raw_affiliation_strings":["Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar, Gujarat, India","institution_ids":["https://openalex.org/I98389781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98389781"],"apc_list":null,"apc_paid":null,"fwci":5.5017,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.96526939,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"12","first_page":"2341","last_page":"2353"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.8213013410568237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7705848217010498},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7382985353469849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7186553478240967},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5908702611923218},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5562983751296997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50604647397995},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49568235874176025},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.45482826232910156},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4500558376312256},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37783050537109375},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.2865385413169861},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26319658756256104}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.8213013410568237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7705848217010498},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7382985353469849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186553478240967},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5908702611923218},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5562983751296997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50604647397995},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49568235874176025},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.45482826232910156},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4500558376312256},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37783050537109375},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2865385413169861},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26319658756256104},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2607341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2607341","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":58,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1542280630","https://openalex.org/W1555696814","https://openalex.org/W1571339265","https://openalex.org/W1635512741","https://openalex.org/W1665214252","https://openalex.org/W1979482308","https://openalex.org/W1982109178","https://openalex.org/W1993721840","https://openalex.org/W2000232298","https://openalex.org/W2012352874","https://openalex.org/W2017399882","https://openalex.org/W2024490156","https://openalex.org/W2057498692","https://openalex.org/W2077804127","https://openalex.org/W2084336274","https://openalex.org/W2093231248","https://openalex.org/W2102113734","https://openalex.org/W2102512139","https://openalex.org/W2107789863","https://openalex.org/W2116064496","https://openalex.org/W2120077739","https://openalex.org/W2130325614","https://openalex.org/W2132037657","https://openalex.org/W2132606418","https://openalex.org/W2133285226","https://openalex.org/W2135623325","https://openalex.org/W2140499889","https://openalex.org/W2153381621","https://openalex.org/W2163922914","https://openalex.org/W2168249605","https://openalex.org/W2193413348","https://openalex.org/W2202505358","https://openalex.org/W2394873997","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2404926044","https://openalex.org/W2406171445","https://openalex.org/W2408093180","https://openalex.org/W2514656709","https://openalex.org/W2546302380","https://openalex.org/W2566553956","https://openalex.org/W2919115771","https://openalex.org/W2963175699","https://openalex.org/W2963211739","https://openalex.org/W6631362777","https://openalex.org/W6637242042","https://openalex.org/W6650649374","https://openalex.org/W6664918268","https://openalex.org/W6675365184","https://openalex.org/W6676071220","https://openalex.org/W6678409544","https://openalex.org/W6687566353","https://openalex.org/W6712560600","https://openalex.org/W6713197546","https://openalex.org/W6713360458","https://openalex.org/W6713450916","https://openalex.org/W6731096007"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W2766680336","https://openalex.org/W1980297060","https://openalex.org/W2133320490","https://openalex.org/W2387604097","https://openalex.org/W4289830142","https://openalex.org/W1497065097","https://openalex.org/W2373675101","https://openalex.org/W3150393935","https://openalex.org/W2125446021"],"abstract_inverted_index":{"To":[0],"learn":[1,56],"auditory":[2],"filterbanks,":[3],"recently,":[4],"we":[5,115,173],"have":[6,92],"proposed":[7,31,216],"an":[8,204],"unsupervised":[9],"learning":[10],"model":[11,45,52,272],"based":[12],"on":[13,181,203,258],"convolutional":[14],"restricted":[15],"Boltzmann":[16],"machine":[17],"(RBM)":[18],"with":[19,46,94,167,197],"rectified":[20],"linear":[21],"units.":[22],"In":[23],"this":[24],"paper,":[25],"theory,":[26],"training":[27,146],"algorithm":[28],"of":[29,36,43,89,119,177,201,240,267,276],"our":[30,215],"model,":[32],"and":[33,74,134,209,224,230,242],"detailed":[34],"analysis":[35],"learned":[37,71,217],"filterbank":[38,103,139,218],"are":[39,61,261],"being":[40],"presented.":[41],"Learning":[42],"the":[44,51,78,148,264],"different":[47],"databases":[48],"shows":[49],"that":[50,60,271],"is":[53,82],"able":[54],"to":[55,84,127,137,187],"cochlear-like":[57],"impulse":[58],"responses":[59],"localized":[62],"in":[63,121,151,179,248],"frequency-domain.":[64],"An":[65],"auditory-like":[66],"scale":[67],"obtained":[68],"from":[69,72],"filterbanks":[70],"clean":[73,229],"noisy":[75],"datasets":[76],"resembles":[77],"Mel":[79,128,138],"scale,":[80],"which":[81],"known":[83],"mimic":[85],"perceptually":[86],"relevant":[87],"aspect":[88],"speech.":[90],"We":[91],"experimented":[93],"both":[95,228],"cepstral":[96,130],"(denoted":[97,105],"as":[98,100,102,106],"ConvRBM-CC)":[99],"well":[101],"features":[104,133,226,244],"ConvRBM-BANK).":[107],"On":[108,142],"large":[109],"vocabulary":[110],"continuous":[111],"speech":[112,233,277],"recognition":[113,234],"task,":[114],"achieved":[116,156],"relative":[117,149,199],"improvement":[118,150,200],"7.21-17.8%":[120],"word":[122],"error":[123],"rate":[124],"(WER)":[125],"compared":[126,136,186],"frequency":[129],"coefficient":[131],"(MFCC)":[132],"1.35-6.82%":[135],"(FBANK)":[140],"features.":[141,169,189],"AURORA":[143,182],"4":[144,183],"multicondition":[145,231],"database,":[147],"WER":[152,180],"by":[153],"4.8-13.65%":[154],"was":[155],"using":[157],"a":[158,198],"Hybrid":[159],"Deep":[160],"Neural":[161],"Network-Hidden":[162],"Markov":[163],"Model":[164],"(DNN-HMM)":[165],"system":[166,193,238],"ConvRBM-CC":[168],"Using":[170],"ConvRBM-BANK":[171,241],"features,":[172],"achieve":[174],"absolute":[175],"reduction":[176],"1.25-3.85%":[178],"test":[184],"sets":[185],"FBANK":[188,243],"A":[190,237],"context-dependent":[191],"DNN-HMM":[192],"further":[194,245],"improves":[195],"performance":[196,247],"3.6-4.6%":[202],"average":[205],"for":[206,227,263],"bigram":[207],"5k":[208,211],"tri-gram":[210],"language":[212],"models.":[213],"Hence,":[214],"performs":[219],"better":[220],"than":[221],"traditional":[222],"MFCC":[223],"Mel-filterbank":[225],"automatic":[232],"(ASR)":[235],"tasks.":[236,251],"combination":[239],"improve":[246],"all":[249],"ASR":[250,265],"Cross-domain":[252],"experiments":[253],"where":[254],"subband":[255],"filters":[256],"trained":[257],"one":[259],"database":[260,269],"used":[262],"task":[266],"another":[268],"show":[270],"learns":[273],"generalized":[274],"representations":[275],"signals.":[278]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}