{"id":"https://openalex.org/W2768731046","doi":"https://doi.org/10.1109/taslp.2017.2738559","title":"Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering","display_name":"Whispered Speech Recognition Using Deep Denoising Autoencoder and Inverse Filtering","publication_year":2017,"publication_date":"2017-11-23","ids":{"openalex":"https://openalex.org/W2768731046","doi":"https://doi.org/10.1109/taslp.2017.2738559","mag":"2768731046"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2738559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2738559","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/A5068153594","display_name":"\u0110or\u0111e Grozdi\u0107","orcid":"https://orcid.org/0000-0002-9812-5236"},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":true,"raw_author_name":"Dorde T. Grozdic","raw_affiliation_strings":["School of Electrical Engineering, University of Belgrade, Belgrade, Serbia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042489636","display_name":"Slobodan T. Jovi\u010di\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4068193","display_name":"University of Belgrade","ror":"https://ror.org/02qsmb048","country_code":"RS","type":"education","lineage":["https://openalex.org/I4068193"]}],"countries":["RS"],"is_corresponding":false,"raw_author_name":"Slobodan T. Jovicic","raw_affiliation_strings":["Life Activities Advancement Center, Laboratory for Forensic Acoustics and Phonetics, Belgrade, Serbia","School of Electrical Engineering, University of Belgrade, Belgrade, Serbia"],"affiliations":[{"raw_affiliation_string":"Life Activities Advancement Center, Laboratory for Forensic Acoustics and Phonetics, Belgrade, Serbia","institution_ids":[]},{"raw_affiliation_string":"School of Electrical Engineering, University of Belgrade, Belgrade, Serbia","institution_ids":["https://openalex.org/I4068193"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068153594"],"corresponding_institution_ids":["https://openalex.org/I4068193"],"apc_list":null,"apc_paid":null,"fwci":5.4047,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.9650998,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"25","issue":"12","first_page":"2313","last_page":"2322"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9753999710083008,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.842815637588501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.812048614025116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7577406167984009},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6631476283073425},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6008792519569397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5144641399383545},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.48690927028656006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48164644837379456},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.44551989436149597},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.36674654483795166},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1825060248374939}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.842815637588501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.812048614025116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577406167984009},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6631476283073425},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6008792519569397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5144641399383545},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.48690927028656006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48164644837379456},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.44551989436149597},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.36674654483795166},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1825060248374939}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2738559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2738559","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":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W96541173","https://openalex.org/W177407077","https://openalex.org/W217071260","https://openalex.org/W242941288","https://openalex.org/W1502652411","https://openalex.org/W1624101316","https://openalex.org/W1984347037","https://openalex.org/W1991893800","https://openalex.org/W2011440797","https://openalex.org/W2022047569","https://openalex.org/W2025768430","https://openalex.org/W2041470347","https://openalex.org/W2055589033","https://openalex.org/W2074936909","https://openalex.org/W2074953333","https://openalex.org/W2087335130","https://openalex.org/W2092239071","https://openalex.org/W2106790438","https://openalex.org/W2108072369","https://openalex.org/W2114537326","https://openalex.org/W2116064496","https://openalex.org/W2117486215","https://openalex.org/W2123133018","https://openalex.org/W2146618065","https://openalex.org/W2155517073","https://openalex.org/W2170160479","https://openalex.org/W2289873871","https://openalex.org/W2294831733","https://openalex.org/W2303272654","https://openalex.org/W2395633578","https://openalex.org/W2397098974","https://openalex.org/W2437658533","https://openalex.org/W2462122138","https://openalex.org/W6607188615","https://openalex.org/W6648342128","https://openalex.org/W6668926045","https://openalex.org/W6685035135","https://openalex.org/W6696449794","https://openalex.org/W6697043880","https://openalex.org/W6712127321","https://openalex.org/W6712664211","https://openalex.org/W6718772350","https://openalex.org/W7008777630"],"related_works":["https://openalex.org/W2606551632","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948"],"abstract_inverted_index":{"Due":[0],"to":[1,34,42],"the":[2,13,60,137],"profound":[3],"differences":[4],"between":[5],"acoustic":[6,54],"characteristics":[7,55],"of":[8,15,56,62,116,120,140,179],"neutral":[9,24],"and":[10,41,69,77,103,125,153,161,165],"whispered":[11,57,63],"speech,":[12,58],"performance":[14],"traditional":[16,108,163],"automatic":[17],"speech":[18,25,64,134],"recognition":[19,65,159,181,186],"(ASR)":[20],"systems":[21],"trained":[22],"on":[23,81,151],"degrades":[26],"significantly":[27,156],"when":[28],"whisper":[29,48,88,105,158,180],"is":[30,136,191],"applied.":[31],"In":[32],"order":[33],"deeply":[35],"analyze":[36],"this":[37,50],"mismatched":[38,67,144],"train/test":[39,145],"situation":[40],"develop":[43],"an":[44,175],"efficient":[45],"way":[46],"for":[47],"recognition,":[49],"study":[51],"first":[52],"analyzes":[53],"addresses":[59],"problems":[61],"in":[66,133,143,174,188],"conditions,":[68],"then":[70],"proposes":[71],"a":[72],"new":[73,148],"robust":[74,102],"cepstral":[75,96,110,117,121],"features":[76],"preprocessing":[78],"approach":[79],"based":[80,150],"deep":[82],"denoising":[83],"autoencoder":[84],"(DDAE)":[85],"that":[86,94,131],"enhance":[87],"recognition.":[89],"The":[90,147,183],"experimental":[91],"results":[92],"confirm":[93],"Teager-energy-based":[95],"features,":[97],"especially":[98],"TECCs,":[99],"are":[100],"more":[101],"better":[104],"descriptors":[106],"than":[107],"Mel-frequency":[109],"coefficients":[111],"(MFCC).":[112],"Further":[113],"detailed":[114],"analysis":[115],"distances,":[118],"distributions":[119],"coefficients,":[122],"confusion":[123],"matrices,":[124],"experiments":[126],"with":[127],"inverse":[128],"filtering,":[129],"prove":[130],"voicing":[132],"stimuli":[135],"main":[138],"cause":[139],"word":[141,185],"misclassification":[142],"scenarios.":[146],"framework":[149],"DDAE":[152],"TECC":[154],"feature,":[155],"improves":[157],"accuracy":[160],"outperforms":[162],"MFCC":[164],"GMM-HMM":[166],"(Gaussian":[167],"mixture":[168],"density-Hidden":[169],"Markov":[170],"model)":[171],"baseline,":[172],"resulting":[173],"absolute":[176],"31%":[177],"improvement":[178],"accuracy.":[182],"achieved":[184],"rate":[187],"neutral/whisper":[189],"scenario":[190],"92.81%.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}