{"id":"https://openalex.org/W4396228962","doi":"https://doi.org/10.3390/fi16050151","title":"Effective Monoaural Speech Separation through Convolutional Top-Down Multi-View Network","display_name":"Effective Monoaural Speech Separation through Convolutional Top-Down Multi-View Network","publication_year":2024,"publication_date":"2024-04-28","ids":{"openalex":"https://openalex.org/W4396228962","doi":"https://doi.org/10.3390/fi16050151"},"language":"en","primary_location":{"id":"doi:10.3390/fi16050151","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16050151","pdf_url":"https://www.mdpi.com/1999-5903/16/5/151/pdf?version=1714369445","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/16/5/151/pdf?version=1714369445","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Aye Nyein Aung","orcid":"https://orcid.org/0009-0003-2294-4221"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Aye Nyein Aung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou 545, Taiwan"],"raw_orcid":"https://orcid.org/0009-0003-2294-4221","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou 545, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041903103","display_name":"Che\u2010Wei Liao","orcid":"https://orcid.org/0000-0001-7156-5381"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Wei Liao","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou 545, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou 545, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019048236","display_name":"Jeih-weih Hung","orcid":"https://orcid.org/0000-0001-9366-3070"},"institutions":[{"id":"https://openalex.org/I193365169","display_name":"National Chi Nan University","ror":"https://ror.org/03ha6v181","country_code":"TW","type":"education","lineage":["https://openalex.org/I193365169"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jeih-Weih Hung","raw_affiliation_strings":["Department of Electrical Engineering, National Chi Nan University, Nantou 545, Taiwan"],"raw_orcid":"https://orcid.org/0000-0001-9366-3070","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, National Chi Nan University, Nantou 545, Taiwan","institution_ids":["https://openalex.org/I193365169"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5019048236"],"corresponding_institution_ids":["https://openalex.org/I193365169"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.6451,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62426976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"5","first_page":"151","last_page":"151"},"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":0.9987999796867371,"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":0.9965999722480774,"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":0.9187474250793457},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5524128675460815},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4444171190261841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34201914072036743},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.3235466480255127},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19008511304855347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9187474250793457},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5524128675460815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4444171190261841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34201914072036743},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.3235466480255127},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19008511304855347}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/fi16050151","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16050151","pdf_url":"https://www.mdpi.com/1999-5903/16/5/151/pdf?version=1714369445","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:16:y:2024:i:5:p:151-:d:1384838","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/16/5/151/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"},{"id":"pmh:oai:doaj.org/article:ce2ef23709e64c2c9e936f6559807234","is_oa":false,"landing_page_url":"https://doaj.org/article/ce2ef23709e64c2c9e936f6559807234","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 16, Iss 5, p 151 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi16050151","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi16050151","pdf_url":"https://www.mdpi.com/1999-5903/16/5/151/pdf?version=1714369445","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396228962.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2069681747","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W3015199127","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3095380484","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3163652268","https://openalex.org/W3191469971","https://openalex.org/W4225309689","https://openalex.org/W4375869348","https://openalex.org/W4391021644","https://openalex.org/W4392903251"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4292513318","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Speech":[0,61],"separation,":[1],"sometimes":[2],"known":[3],"as":[4],"the":[5,10,33,102,106,166,177,195,205,219,229,233,236,242],"\u201ccocktail":[6],"party":[7],"problem\u201d,":[8],"is":[9,30,67,173,210],"process":[11],"of":[12,114,130,235,244],"separating":[13],"individual":[14],"speech":[15,35,78,85,107,112,117,143,168,191],"signals":[16],"from":[17],"an":[18],"audio":[19,65],"mixture":[20,108],"that":[21,53,223],"includes":[22],"ambient":[23],"noises":[24],"and":[25,41,80,109,155,187,198],"several":[26],"speakers.":[27],"The":[28,171],"goal":[29],"to":[31,46,100],"extract":[32],"target":[34],"in":[36,58,208,228],"this":[37],"complicated":[38],"sound":[39],"scenario":[40],"either":[42],"make":[43],"it":[44,54],"easier":[45],"understand":[47],"or":[48],"increase":[49],"its":[50],"quality":[51],"so":[52],"may":[55],"be":[56],"used":[57],"subsequent":[59],"processing.":[60],"separation":[62,86,118,144,150,169],"on":[63,91,218],"overlapping":[64],"data":[66],"important":[68],"for":[69,189],"many":[70],"speech-processing":[71],"tasks,":[72],"including":[73],"natural":[74],"language":[75],"processing,":[76],"automatic":[77],"recognition,":[79],"intelligent":[81],"personal":[82],"assistants.":[83],"New":[84],"algorithms":[87,119],"are":[88],"often":[89],"built":[90],"a":[92,128,133,140,213],"deep":[93],"neural":[94],"network":[95,145,172],"(DNN)":[96],"structure,":[97],"which":[98,158,180],"seeks":[99],"learn":[101],"complex":[103],"relationship":[104],"between":[105],"any":[110],"specific":[111],"source":[113],"interest.":[115],"DNN-based":[116],"outperform":[120],"conventional":[121],"statistics-based":[122],"methods,":[123],"although":[124],"they":[125],"typically":[126],"need":[127],"lot":[129],"processing":[131],"and/or":[132],"larger":[134],"model":[135,162],"size.":[136],"This":[137],"study":[138],"presents":[139],"new":[141],"end-to-end":[142],"called":[146],"ESC-MASD-Net":[147,193,209,224],"(effective":[148],"speaker":[149],"through":[151],"convolutional":[152],"multi-view":[153,196],"attention":[154,197],"SuDoRM-RF":[156],"network),":[157],"has":[159,239],"relatively":[160],"fewer":[161],"parameters":[163],"compared":[164],"with":[165,185,212],"state-of-the-art":[167],"architectures.":[170],"partly":[174],"inspired":[175],"by":[176],"SuDoRM-RF++":[178,226],"network,":[179],"uses":[181],"multiple":[182],"time-resolution":[183],"features":[184],"downsampling":[186],"resampling":[188],"effective":[190],"separation.":[192],"incorporates":[194],"residual":[199],"conformer":[200,214,237],"modules":[201],"into":[202],"SuDoRM-RF++.":[203],"Additionally,":[204],"U-Convolutional":[206],"block":[207],"refined":[211],"layer.":[215],"Experiments":[216],"conducted":[217],"WHAM!":[220],"dataset":[221],"show":[222],"outperforms":[225],"significantly":[227],"SI-SDRi":[230],"metric.":[231],"Furthermore,":[232],"use":[234],"layer":[238],"also":[240],"improved":[241],"performance":[243],"ESC-MASD-Net.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}