{"id":"https://openalex.org/W4312499001","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892355","title":"Two-Stage Deep Learning Approach for Speech Enhancement and Reconstruction in The Frequency and Time Domains","display_name":"Two-Stage Deep Learning Approach for Speech Enhancement and Reconstruction in The Frequency and Time Domains","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312499001","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892355"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892355","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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/A5060665993","display_name":"Soha A. Nossier","orcid":"https://orcid.org/0000-0001-6383-254X"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Soha A. Nossier","raw_affiliation_strings":["University of East London,Dept. of Engineering and Computing,London,UK","Dept. of Engineering and Computing, University of East London, London, UK"],"affiliations":[{"raw_affiliation_string":"University of East London,Dept. of Engineering and Computing,London,UK","institution_ids":["https://openalex.org/I157227730"]},{"raw_affiliation_string":"Dept. of Engineering and Computing, University of East London, London, UK","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063632288","display_name":"Julie Wall","orcid":"https://orcid.org/0000-0001-6714-4867"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Julie Wall","raw_affiliation_strings":["University of East London,Dept. of Engineering and Computing,London,UK","Dept. of Engineering and Computing, University of East London, London, UK"],"affiliations":[{"raw_affiliation_string":"University of East London,Dept. of Engineering and Computing,London,UK","institution_ids":["https://openalex.org/I157227730"]},{"raw_affiliation_string":"Dept. of Engineering and Computing, University of East London, London, UK","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087019252","display_name":"M. Moniri","orcid":"https://orcid.org/0000-0002-5564-0692"},"institutions":[{"id":"https://openalex.org/I157227730","display_name":"University of East London","ror":"https://ror.org/057jrqr44","country_code":"GB","type":"education","lineage":["https://openalex.org/I157227730"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mansour Moniri","raw_affiliation_strings":["University of East London,Dept. of Engineering and Computing,London,UK","Dept. of Engineering and Computing, University of East London, London, UK"],"affiliations":[{"raw_affiliation_string":"University of East London,Dept. of Engineering and Computing,London,UK","institution_ids":["https://openalex.org/I157227730"]},{"raw_affiliation_string":"Dept. of Engineering and Computing, University of East London, London, UK","institution_ids":["https://openalex.org/I157227730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044554092","display_name":"Cornelius Glackin","orcid":"https://orcid.org/0000-0001-5114-6403"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cornelius Glackin","raw_affiliation_strings":["Intelligent Voice Ltd,London,UK","Intelligent Voice Ltd, London, UK"],"affiliations":[{"raw_affiliation_string":"Intelligent Voice Ltd,London,UK","institution_ids":["https://openalex.org/I4210153682"]},{"raw_affiliation_string":"Intelligent Voice Ltd, London, UK","institution_ids":["https://openalex.org/I4210153682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012466886","display_name":"Nigel Cannings","orcid":"https://orcid.org/0000-0002-5279-3968"},"institutions":[{"id":"https://openalex.org/I4210153682","display_name":"Intelligent Health (United Kingdom)","ror":"https://ror.org/0576zak10","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210153682"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nigel Cannings","raw_affiliation_strings":["Intelligent Voice Ltd,London,UK","Intelligent Voice Ltd, London, UK"],"affiliations":[{"raw_affiliation_string":"Intelligent Voice Ltd,London,UK","institution_ids":["https://openalex.org/I4210153682"]},{"raw_affiliation_string":"Intelligent Voice Ltd, London, UK","institution_ids":["https://openalex.org/I4210153682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5060665993"],"corresponding_institution_ids":["https://openalex.org/I157227730"],"apc_list":null,"apc_paid":null,"fwci":0.8591,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74755134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9968000054359436,"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":0.9871000051498413,"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/computer-science","display_name":"Computer science","score":0.7767068147659302},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7375997304916382},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7068072557449341},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6988256573677063},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6959752440452576},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6007145643234253},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5714375376701355},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5610557794570923},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.5428285002708435},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5157842636108398},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49475497007369995},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.424399197101593},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4139895439147949},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37202292680740356},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08694285154342651},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07858502864837646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767068147659302},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7375997304916382},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7068072557449341},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6988256573677063},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6959752440452576},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6007145643234253},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5714375376701355},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5610557794570923},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.5428285002708435},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5157842636108398},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49475497007369995},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.424399197101593},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4139895439147949},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37202292680740356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08694285154342651},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07858502864837646},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892355","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892355","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.uel.ac.uk:8qq14","is_oa":false,"landing_page_url":"https://doi.org/10.1109/IJCNN55064.2022.9892355","pdf_url":null,"source":{"id":"https://openalex.org/S4306401301","display_name":"UEL Research Repository (University of East London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157227730","host_organization_name":"University of East London","host_organization_lineage":["https://openalex.org/I157227730"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference-paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"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":58,"referenced_works":["https://openalex.org/W258661521","https://openalex.org/W1494198834","https://openalex.org/W1516630152","https://openalex.org/W1974387177","https://openalex.org/W2048142341","https://openalex.org/W2048510784","https://openalex.org/W2069681747","https://openalex.org/W2094721231","https://openalex.org/W2128653836","https://openalex.org/W2140828385","https://openalex.org/W2141998673","https://openalex.org/W2144404214","https://openalex.org/W2153894152","https://openalex.org/W2291877678","https://openalex.org/W2404892923","https://openalex.org/W2409959948","https://openalex.org/W2757519008","https://openalex.org/W2802304149","https://openalex.org/W2889286744","https://openalex.org/W2890820256","https://openalex.org/W2919115771","https://openalex.org/W2936689732","https://openalex.org/W2949558265","https://openalex.org/W2952979007","https://openalex.org/W2963045393","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963840672","https://openalex.org/W2971417062","https://openalex.org/W2972443522","https://openalex.org/W2980451698","https://openalex.org/W2998155746","https://openalex.org/W2998572311","https://openalex.org/W2998832642","https://openalex.org/W3015197852","https://openalex.org/W3015219411","https://openalex.org/W3015526955","https://openalex.org/W3016120385","https://openalex.org/W3016129867","https://openalex.org/W3017350693","https://openalex.org/W3032514799","https://openalex.org/W3049430014","https://openalex.org/W3089552252","https://openalex.org/W3091570562","https://openalex.org/W3097945073","https://openalex.org/W3100777112","https://openalex.org/W3102190437","https://openalex.org/W3113609448","https://openalex.org/W3147539069","https://openalex.org/W3162420637","https://openalex.org/W3197042120","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W6629717138","https://openalex.org/W6696085341","https://openalex.org/W6756251360","https://openalex.org/W6762114000","https://openalex.org/W6772349387"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2342810974","https://openalex.org/W2058482658","https://openalex.org/W2988616598","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W2037635165","https://openalex.org/W4287113595","https://openalex.org/W3176271478","https://openalex.org/W4312751558"],"abstract_inverted_index":{"Deep":[0],"learning":[1,74],"has":[2],"recently":[3],"shown":[4],"promising":[5],"improvement":[6,117,160],"in":[7,16,76,81,95,106,118,161],"the":[8,23,27,61,82,96,107,119,129,135,140,178],"speech":[9,30,35,49,102,131],"enhancement":[10,50,132],"field,":[11],"due":[12],"to":[13,55,63,155,177],"its":[14],"effectiveness":[15],"eliminating":[17],"noise.":[18],"However,":[19],"a":[20,44,72,91,145,151],"drawback":[21],"of":[22,29,128,164],"denoising":[24,47,78,100],"process":[25],"is":[26,53,79],"introduction":[28],"distortion,":[31],"which":[32,77],"negatively":[33],"affects":[34],"quality":[36],"and":[37,66,101,148,158,168],"intelligibility.":[38],"In":[39],"this":[40],"work,":[41],"we":[42,70],"propose":[43],"deep":[45],"convolutional":[46],"autoencoder-based":[48],"network":[51],"that":[52,112],"designed":[54],"have":[56],"an":[57],"encoder":[58],"deeper":[59],"than":[60],"decoder,":[62],"improve":[64],"performance":[65],"decrease":[67],"complexity.":[68],"Furthermore,":[69],"present":[71],"two-stage":[73],"approach,":[75],"performed":[80,105],"first":[83],"frequency":[84],"domain":[85],"stage":[86],"using":[87,134,144,150],"magnitude":[88],"spectrum":[89],"as":[90],"training":[92],"target;":[93],"while,":[94],"second":[97],"stage,":[98],"further":[99],"reconstruction":[103],"are":[104],"time":[108],"domain.":[109],"Results":[110],"show":[111],"our":[113],"architecture":[114,141],"achieves":[115],"0.22":[116],"overall":[120],"predicted":[121],"mean":[122],"opinion":[123],"score":[124],"(Covl)":[125],"over":[126],"state":[127],"art":[130],"architectures,":[133],"Valentini":[136],"dataset":[137,147],"benchmark.":[138],"Moreover,":[139],"was":[142],"trained":[143],"larger":[146],"tested":[149],"mismatched":[152],"test":[153],"corpus,":[154],"achieve":[156],"0.7":[157],"6.35%":[159],"Perceptual":[162],"Evaluation":[163],"Speech":[165],"Quality":[166],"(PESQ)":[167],"Short":[169],"Time":[170],"Objective":[171],"Intelligibility":[172],"(STOI)":[173],"scores,":[174],"respectively,":[175],"compared":[176],"noisy":[179],"speech.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}