{"id":"https://openalex.org/W2985059374","doi":"https://doi.org/10.23919/eusipco.2019.8902710","title":"Clean speech AE-DNN PSD constraint for MCLP based reverberant speech enhancement","display_name":"Clean speech AE-DNN PSD constraint for MCLP based reverberant speech enhancement","publication_year":2019,"publication_date":"2019-09-01","ids":{"openalex":"https://openalex.org/W2985059374","doi":"https://doi.org/10.23919/eusipco.2019.8902710","mag":"2985059374"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2019.8902710","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th 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/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srikanth Raj Chetupalli","raw_affiliation_strings":["Department of Electrical Communication Engineering, Indian Institute of Science, Bengaluru"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Communication Engineering, Indian Institute of Science, Bengaluru","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069425803","display_name":"T.V. Sreenivas","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Thippur V. Sreenivas","raw_affiliation_strings":["Department of Electrical Communication Engineering, Indian Institute of Science, Bengaluru"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Communication Engineering, Indian Institute of Science, Bengaluru","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.167,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46777041,"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7310064435005188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.639145016670227},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.579108476638794},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5581310987472534},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.49579986929893494},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.49032095074653625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4545925259590149},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.4461909234523773},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4238497018814087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3647294044494629},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.27990829944610596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18278810381889343},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09463360905647278},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.07207313179969788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7310064435005188},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.639145016670227},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.579108476638794},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5581310987472534},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.49579986929893494},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.49032095074653625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4545925259590149},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.4461909234523773},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4238497018814087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3647294044494629},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.27990829944610596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18278810381889343},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09463360905647278},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.07207313179969788},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco.2019.8902710","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2019.8902710","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 27th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"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":25,"referenced_works":["https://openalex.org/W4416539","https://openalex.org/W6908809","https://openalex.org/W7560395","https://openalex.org/W19178994","https://openalex.org/W1546020483","https://openalex.org/W1552314771","https://openalex.org/W1983812858","https://openalex.org/W2006129368","https://openalex.org/W2042061909","https://openalex.org/W2067295501","https://openalex.org/W2096819401","https://openalex.org/W2163674618","https://openalex.org/W2163680580","https://openalex.org/W2164502538","https://openalex.org/W2165534711","https://openalex.org/W2176412452","https://openalex.org/W2242685705","https://openalex.org/W2537346279","https://openalex.org/W2609317876","https://openalex.org/W2747732471","https://openalex.org/W2963285578","https://openalex.org/W4231225162","https://openalex.org/W6600284362","https://openalex.org/W6600294567","https://openalex.org/W6685562342"],"related_works":["https://openalex.org/W2363301696","https://openalex.org/W2352223112","https://openalex.org/W1570840316","https://openalex.org/W2139283974","https://openalex.org/W4312036005","https://openalex.org/W2383072803","https://openalex.org/W2144045625","https://openalex.org/W3018445606","https://openalex.org/W3211091508","https://openalex.org/W72660888"],"abstract_inverted_index":{"Blind":[0],"inverse":[1],"filtering":[2],"using":[3,121],"multi-channel":[4],"linear":[5],"prediction":[6,30,40],"(MCLP)":[7],"in":[8,43],"short-time":[9],"Fourier":[10],"transform":[11],"(STFT)":[12],"domain":[13],"is":[14,35,49,88],"an":[15,63],"effective":[16],"means":[17],"to":[18,37,51,93],"enhance":[19],"reverberant":[20,140],"speech.":[21],"Traditionally,":[22],"a":[23],"speech":[24,85,98],"power":[25],"spectral":[26],"density":[27],"(PSD)":[28],"weighted":[29],"error":[31],"(WPE)":[32],"minimization":[33],"approach":[34],"used":[36,89],"estimate":[38,132],"the":[39,52,73,91,96,106,128,136],"filters,":[41],"independently":[42],"each":[44],"frequency":[45],"bin.":[46],"The":[47],"method":[48],"sensitive":[50],"estimation":[53,74],"of":[54,75],"desired":[55,76],"signal":[56,77,141],"PSD.":[57,78,99],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"auto-encoder":[64],"(AE)":[65],"deep":[66],"neural":[67],"network":[68],"(DNN)":[69],"based":[70,130],"constraint":[71],"for":[72,105,139],"An":[79],"auto":[80],"encoder":[81],"trained":[82],"on":[83],"clean":[84],"STFT":[86],"coefficients":[87],"as":[90],"prior":[92],"non-linearly":[94],"map":[95],"natural":[97],"We":[100],"explore":[101],"two":[102],"different":[103],"architectures":[104],"auto-encoder:":[107],"(i)":[108],"fully-connected":[109],"(FC)":[110],"feed-forward,":[111],"and":[112],"(ii)":[113],"recurrent":[114],"long":[115],"short-term":[116],"memory":[117],"(LSTM)":[118],"architecture.":[119],"Experiments":[120],"real":[122],"room":[123],"impulse":[124],"responses":[125],"show":[126],"that":[127],"LSTM-DNN":[129],"PSD":[131],"performs":[133],"better":[134],"than":[135],"traditional":[137],"methods":[138],"enhancement.":[142]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}