{"id":"https://openalex.org/W2902061565","doi":"https://doi.org/10.23919/eusipco.2018.8553339","title":"Integrating Denoising Autoencoder and Vector Taylor Series with Auditory Masking for Speech Recognition in Noisy Conditions","display_name":"Integrating Denoising Autoencoder and Vector Taylor Series with Auditory Masking for Speech Recognition in Noisy Conditions","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2902061565","doi":"https://doi.org/10.23919/eusipco.2018.8553339","mag":"2902061565"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553339","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-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/A5025520963","display_name":"Abhijit Das","orcid":"https://orcid.org/0000-0002-6793-0582"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210131512","display_name":"Centre Inria de l'universit\u00e9 de Bordeaux","ror":"https://ror.org/03tjcj052","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210131512"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"A. Biswajit Das","raw_affiliation_strings":["INRIA Bordeaux Sud-Ouest (GeoStat team), Talence, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Bordeaux Sud-Ouest (GeoStat team), Talence, France","institution_ids":["https://openalex.org/I4210131512","https://openalex.org/I1326498283"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103959037","display_name":"Ashish Panda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashish Panda","raw_affiliation_strings":["TCS Innovation Labs-Mumbai, Thane, Maharashtra, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Innovation Labs-Mumbai, Thane, Maharashtra, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3325,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58606531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2305","last_page":"2309"},"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":0.9994000196456909,"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":0.9991999864578247,"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/timit","display_name":"TIMIT","score":0.8085414171218872},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7651503086090088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7221136689186096},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5824843049049377},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.547805666923523},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5177123546600342},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5163144469261169},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48115479946136475},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.46257808804512024},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45379459857940674},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4009447395801544},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.19290703535079956}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8085414171218872},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7651503086090088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7221136689186096},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5824843049049377},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.547805666923523},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5177123546600342},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5163144469261169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48115479946136475},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.46257808804512024},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45379459857940674},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4009447395801544},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.19290703535079956},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2018.8553339","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W67398352","https://openalex.org/W1524333225","https://openalex.org/W1601124178","https://openalex.org/W1973681148","https://openalex.org/W1988843652","https://openalex.org/W2076502758","https://openalex.org/W2085083351","https://openalex.org/W2116746197","https://openalex.org/W2117671523","https://openalex.org/W2122514667","https://openalex.org/W2137401359","https://openalex.org/W2173629880","https://openalex.org/W2283531158","https://openalex.org/W2290318471","https://openalex.org/W2293634267","https://openalex.org/W2396756519","https://openalex.org/W2406171445","https://openalex.org/W2515753980","https://openalex.org/W2544142255","https://openalex.org/W2671186495","https://openalex.org/W2750418488","https://openalex.org/W6631362777","https://openalex.org/W6677326886","https://openalex.org/W6677592687","https://openalex.org/W6680646222","https://openalex.org/W6696830301","https://openalex.org/W6696934422","https://openalex.org/W6712567857","https://openalex.org/W6713360458"],"related_works":["https://openalex.org/W3037110488","https://openalex.org/W4375869169","https://openalex.org/W2597829360","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W2131486661","https://openalex.org/W2153897396","https://openalex.org/W2005805562","https://openalex.org/W2115778783","https://openalex.org/W2538939196"],"abstract_inverted_index":{"We":[0,116,140],"propose":[1,117],"a":[2,22,89,101,118],"new":[3,119],"front-end":[4],"feature":[5],"compensation":[6,103,132],"technique":[7,145],"to":[8,34,72,88,133],"improve":[9,93],"the":[10,36,52,56,63,67,77,80,85,94,106,129,143,147],"performance":[11,45,86,96,138,149],"of":[12,79,131],"Automatic":[13],"Speech":[14],"Recognition":[15],"(ASR)":[16],"systems":[17],"in":[18,44,55,66,76,97],"noisy":[19,37],"environments.":[20],"First,":[21],"Time":[23],"Delay":[24],"Neural":[25],"Network":[26],"(TDNN)":[27],"based":[28,123],"Denoising":[29],"Autoencoder":[30],"(DAE)":[31],"is":[32,70,114],"considered":[33],"compensate":[35],"features.":[38],"The":[39],"DAE":[40,81],"provides":[41],"good":[42],"gain":[43],"when":[46],"it":[47],"has":[48],"been":[49],"trained":[50],"using":[51],"noise":[53,64,152],"present":[54,65],"test":[57,68],"utterances":[58],"(\u201cseen\u201d":[59],"conditions).":[60],"However,":[61],"if":[62],"utterance":[69],"different":[71],"what":[73],"was":[74],"used":[75,135],"training":[78],"(\u201cun-seen\u201d":[82],"conditions),":[83],"then":[84],"degrades":[87],"great":[90],"extent.":[91],"To":[92],"ASR":[95,148],"such":[98],"unseen":[99],"conditions,":[100],"model":[102],"technique,":[104],"namely":[105],"Vector":[107],"Taylor":[108],"Series":[109],"with":[110],"Auditory":[111],"Masking":[112],"(VTS-AM)":[113],"used.":[115],"Signal-to-Noise":[120],"Ratio":[121],"(SNR)":[122],"measure,":[124],"which":[125],"can":[126],"reliably":[127],"choose":[128],"type":[130],"be":[134],"for":[136],"best":[137],"gain.":[139],"show":[141],"that":[142],"proposed":[144],"improves":[146],"significantly":[150],"on":[151],"corrupted":[153],"TIMIT":[154],"and":[155],"Librispeech":[156],"databases.":[157]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}