{"id":"https://openalex.org/W4375947632","doi":"https://doi.org/10.3233/jifs-223951","title":"DCT based densely connected convolutional GRU for real-time speech enhancement","display_name":"DCT based densely connected convolutional GRU for real-time speech enhancement","publication_year":2023,"publication_date":"2023-05-09","ids":{"openalex":"https://openalex.org/W4375947632","doi":"https://doi.org/10.3233/jifs-223951"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-223951","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-223951","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","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/A5062350695","display_name":"Chaitanya Jannu","orcid":"https://orcid.org/0000-0003-0980-8076"},"institutions":[{"id":"https://openalex.org/I4401726783","display_name":"VIT-AP University","ror":"https://ror.org/007v4hf75","country_code":null,"type":"education","lineage":["https://openalex.org/I4401726783"]},{"id":"https://openalex.org/I4210131147","display_name":"SRM University","ror":"https://ror.org/037skf023","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018","https://openalex.org/I4210131147"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Chaitanya Jannu","raw_affiliation_strings":["School of Electronics Engineering, VIT-AP University, Amaravati, India"],"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, VIT-AP University, Amaravati, India","institution_ids":["https://openalex.org/I4210131147","https://openalex.org/I4401726783"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049162806","display_name":"Sunny Dayal Vanambathina","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726783","display_name":"VIT-AP University","ror":"https://ror.org/007v4hf75","country_code":null,"type":"education","lineage":["https://openalex.org/I4401726783"]},{"id":"https://openalex.org/I4210131147","display_name":"SRM University","ror":"https://ror.org/037skf023","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018","https://openalex.org/I4210131147"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sunny Dayal Vanambathina","raw_affiliation_strings":["School of Electronics Engineering, VIT-AP University, Amaravati, India"],"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, VIT-AP University, Amaravati, India","institution_ids":["https://openalex.org/I4210131147","https://openalex.org/I4401726783"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062350695"],"corresponding_institution_ids":["https://openalex.org/I4210131147","https://openalex.org/I4401726783"],"apc_list":null,"apc_paid":null,"fwci":1.8608,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86019916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"45","issue":"1","first_page":"1195","last_page":"1208"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9951000213623047,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.9405180811882019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8043068647384644},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6852034330368042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6648833751678467},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5658060312271118},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.5100858807563782},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47816354036331177},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4599757194519043},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42123815417289734},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4169941842556},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.386314332485199},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.33777758479118347},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3344682455062866}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9405180811882019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043068647384644},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6852034330368042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6648833751678467},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5658060312271118},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.5100858807563782},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47816354036331177},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4599757194519043},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42123815417289734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4169941842556},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.386314332485199},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.33777758479118347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3344682455062866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-223951","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-223951","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2031614119","https://openalex.org/W2069681747","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2086139506","https://openalex.org/W2117678320","https://openalex.org/W2291877678","https://openalex.org/W2535388113","https://openalex.org/W2598036111","https://openalex.org/W2892110446","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W3099330747","https://openalex.org/W3134695619"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W4386746628","https://openalex.org/W2037635165"],"abstract_inverted_index":{"Over":[0],"the":[1,12,19,43,47,57,64,69,98,101,134,144,149,157,165,184,198,207,211,226],"past":[2],"ten":[3],"years,":[4],"deep":[5,89],"learning":[6],"has":[7],"enabled":[8],"significant":[9],"advancements":[10],"in":[11,45,53,197,215],"improvement":[13],"of":[14,23,42,63,68,100,148,200,217,225],"noisy":[15,188],"speech.":[16,48],"Due":[17],"to":[18,76],"short":[20],"time":[21],"stability":[22],"speech":[24,27,65,70,189,227],"signal,":[25],"previous":[26,141],"enhancement":[28,71],"(SE)":[29],"methods":[30,38],"concentrated":[31],"only":[32],"on":[33],"magnitude":[34],"estimation,":[35],"and":[36,127,164,229],"these":[37,54],"added":[39,196],"a":[40,111,169,191],"phase":[41,58],"mixture":[44],"reconstructing":[46],"The":[49,130,146,202],"performance":[50],"is":[51,103,152,195],"limited":[52],"approaches":[55,72],"since":[56],"will":[59],"also":[60],"carry":[61],"some":[62],"information.":[66],"Some":[67],"were":[73],"developed":[74],"later":[75],"jointly":[77],"estimate":[78],"both":[79],"magnitudes":[80],"as":[81,83],"well":[82],"phases.":[84],"Recently,":[85],"complex-valued":[86],"models,":[87],"like":[88],"complex":[90],"convolution":[91],"recurrent":[92],"network":[93],"(DCCRN),":[94],"are":[95],"proposed,":[96],"but":[97],"computation":[99],"model":[102,122,209],"very":[104],"huge.":[105],"In":[106],"this":[107],"work,":[108],"we":[109],"propose":[110],"Discrete":[112],"Cosine":[113],"Transform-based":[114],"Densely":[115],"Connected":[116],"Convolutional":[117],"Gated":[118],"Recurrent":[119],"Unit":[120],"(DCTDCCGRU)":[121],"using":[123],"dilated":[124,158],"dense":[125,131,150,166],"block":[126,151],"stacked":[128],"GRU.":[129],"connectivity":[132,167],"strengthens":[133],"gradient":[135],"propagation":[136],"by":[137,177],"concatenating":[138],"features":[139],"from":[140],"layers":[142],"at":[143,154],"input.":[145],"advantage":[147],"that":[153,206],"various":[155],"resolutions,":[156],"convolutions":[159],"aid":[160],"with":[161,172],"context":[162],"aggregation,":[163],"provides":[168],"feature":[170],"map":[171],"more":[173],"precise":[174],"target":[175],"information":[176],"passing":[178],"through":[179],"multiple":[180],"layers.":[181],"To":[182],"represent":[183],"correlation":[185],"between":[186],"neighboring":[187],"frames,":[190],"two":[192],"Layer":[193],"GRU":[194],"bottleneck":[199],"U-Net.":[201],"experimental":[203],"findings":[204],"demonstrate":[205],"proposed":[208],"outperformed":[210],"other":[212],"existing":[213],"models":[214],"terms":[216],"STOI":[218],"(short-time":[219],"objective":[220],"intelligibility),":[221],"PESQ":[222],"(perceptual":[223],"evaluation":[224],"quality),":[228],"output":[230],"SNR":[231],"(signal-to-noise":[232],"ratio).":[233]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}