{"id":"https://openalex.org/W4224931713","doi":"https://doi.org/10.1109/icassp43922.2022.9747752","title":"Cross-Domain Speech Enhancement with a Neural Cascade Architecture","display_name":"Cross-Domain Speech Enhancement with a Neural Cascade Architecture","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931713","doi":"https://doi.org/10.1109/icassp43922.2022.9747752","pmid":"https://pubmed.ncbi.nlm.nih.gov/40330427"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747752","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","pubmed"],"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/A5101497068","display_name":"Heming Wang","orcid":"https://orcid.org/0000-0003-3057-9060"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Heming Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2022","issue":null,"first_page":"7862","last_page":"7866"},"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":0.998199999332428,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/computer-science","display_name":"Computer science","score":0.7691565752029419},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7648774981498718},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.7357614040374756},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6791117787361145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6783056855201721},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5446304082870483},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5257740020751953},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.47129523754119873},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3878597021102905},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34095925092697144},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.22281688451766968},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07351189851760864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691565752029419},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7648774981498718},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.7357614040374756},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6791117787361145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6783056855201721},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5446304082870483},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5257740020751953},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.47129523754119873},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3878597021102905},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34095925092697144},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.22281688451766968},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07351189851760864},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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/C42360764","wikidata":"https://www.wikidata.org/wiki/Q83588","display_name":"Chemical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747752","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmid:40330427","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40330427","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:europepmc.org:10867414","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12051458","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2910152985","display_name":null,"funder_award_id":"R01 DC012048","funder_id":"https://openalex.org/F4320337352","funder_display_name":"National Institute on Deafness and Other Communication Disorders"}],"funders":[{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"},{"id":"https://openalex.org/F4320337352","display_name":"National Institute on Deafness and Other Communication Disorders","ror":"https://ror.org/04mhx6838"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1536373746","https://openalex.org/W1552314771","https://openalex.org/W1901129140","https://openalex.org/W1974387177","https://openalex.org/W2024490156","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2291877678","https://openalex.org/W2516001803","https://openalex.org/W2889442120","https://openalex.org/W2943554574","https://openalex.org/W2962866211","https://openalex.org/W2963446712","https://openalex.org/W2972693890","https://openalex.org/W2981436548","https://openalex.org/W2991361823","https://openalex.org/W3015679215","https://openalex.org/W3096408984","https://openalex.org/W3134695619","https://openalex.org/W3162493033","https://openalex.org/W3177933256","https://openalex.org/W3201698955","https://openalex.org/W3211408542","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W6639824700","https://openalex.org/W6756251360","https://openalex.org/W6791665418","https://openalex.org/W6797805884"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,63,76],"novel":[4],"cascade":[5,41],"architecture":[6,42],"to":[7,29],"address":[8],"the":[9,32,51,56,59,69,81],"monaural":[10],"speech":[11,20,65,103],"enhancement":[12,92],"problem.":[13],"We":[14],"leverage":[15],"three":[16,45],"different":[17],"domains":[18],"of":[19,44,58,101],"representation,":[21],"namely":[22],"spectral":[23],"magnitude,":[24],"waveform,":[25],"and":[26,47,55,94,105],"complex":[27],"spectrogram,":[28],"progressively":[30],"suppress":[31],"background":[33],"noise":[34],"within":[35],"noisy":[36,53],"speech.":[37],"Our":[38],"proposed":[39,88],"neural":[40],"consists":[43],"modules,":[46],"each":[48],"operates":[49],"on":[50,80],"original":[52],"input":[54],"output":[57],"previous":[60,97],"module":[61],"in":[62,99],"distinct":[64],"representation.":[66],"During":[67],"training,":[68],"network":[70],"simultaneously":[71],"optimizes":[72],"all":[73],"modules":[74],"with":[75],"triple-domain":[77],"loss.":[78],"Experiments":[79],"WSJ0":[82],"SI-84":[83],"corpus":[84],"demonstrate":[85],"that":[86],"our":[87],"approach":[89],"achieves":[90],"superior":[91],"results,":[93],"substantially":[95],"outperforms":[96],"baselines":[98],"terms":[100],"both":[102],"quality":[104],"intelligibility.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}
