{"id":"https://openalex.org/W4285197326","doi":"https://doi.org/10.1109/access.2022.3188712","title":"Speech Separation Using Augmented-Discrimination Learning on Squash-Norm Embedding Vector and Node Encoder","display_name":"Speech Separation Using Augmented-Discrimination Learning on Squash-Norm Embedding Vector and Node Encoder","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285197326","doi":"https://doi.org/10.1109/access.2022.3188712"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3188712","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3188712","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09815249.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09815249.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056726536","display_name":"Ha Minh Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ha Minh Tan","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101451175","display_name":"Kai-Wen Liang","orcid":"https://orcid.org/0000-0002-7130-1957"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Wen Liang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026413645","display_name":"Yuan-Shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Shan Lee","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022504648","display_name":"Chung-Ting Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113837","display_name":"Taiwan Forestry Research Institute","ror":"https://ror.org/01d34a364","country_code":"TW","type":"facility","lineage":["https://openalex.org/I26359584","https://openalex.org/I4210113837"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Ting Li","raw_affiliation_strings":["AI Research Center, Hon Hai Research Institute, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"AI Research Center, Hon Hai Research Institute, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210113837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048205934","display_name":"Yung\u2010Hui Li","orcid":"https://orcid.org/0000-0002-0475-3689"},"institutions":[{"id":"https://openalex.org/I4210113837","display_name":"Taiwan Forestry Research Institute","ror":"https://ror.org/01d34a364","country_code":"TW","type":"facility","lineage":["https://openalex.org/I26359584","https://openalex.org/I4210113837"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yung-Hui Li","raw_affiliation_strings":["AI Research Center, Hon Hai Research Institute, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"AI Research Center, Hon Hai Research Institute, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210113837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056726536"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.6812,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90451968,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"10","issue":null,"first_page":"102048","last_page":"102063"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9961000084877014,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6712584495544434},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6290013790130615},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.48385846614837646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4529586434364319},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.4487614929676056},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4383925795555115},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.437834769487381},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43709033727645874},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4285942018032074}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6712584495544434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6290013790130615},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.48385846614837646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4529586434364319},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4487614929676056},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4383925795555115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.437834769487381},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43709033727645874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4285942018032074},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3188712","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3188712","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09815249.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:54697f9604a946f682ea78a48646944b","is_oa":true,"landing_page_url":"https://doaj.org/article/54697f9604a946f682ea78a48646944b","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 102048-102063 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3188712","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3188712","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09815249.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1288377535","display_name":null,"funder_award_id":"MOST 110-2221-E-008-076-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G2313227155","display_name":null,"funder_award_id":"MOST 111-2321-B-195-001","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G2990462017","display_name":null,"funder_award_id":"MOST 110-2634-F-008-008","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G800543846","display_name":null,"funder_award_id":"MOST 110-2634-F-008-004","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"},{"id":"https://openalex.org/G8912898309","display_name":null,"funder_award_id":"MOST 110-2634-F-006-022","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285197326.pdf","grobid_xml":"https://content.openalex.org/works/W4285197326.grobid-xml"},"referenced_works_count":69,"referenced_works":["https://openalex.org/W80444264","https://openalex.org/W165783309","https://openalex.org/W185399533","https://openalex.org/W1485161427","https://openalex.org/W1552314771","https://openalex.org/W1602144089","https://openalex.org/W1635512741","https://openalex.org/W1780344239","https://openalex.org/W1987906574","https://openalex.org/W2031647436","https://openalex.org/W2037351952","https://openalex.org/W2053165762","https://openalex.org/W2069681747","https://openalex.org/W2088361146","https://openalex.org/W2100495367","https://openalex.org/W2127851351","https://openalex.org/W2130178255","https://openalex.org/W2133340843","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2146608839","https://openalex.org/W2149425615","https://openalex.org/W2150376021","https://openalex.org/W2150415460","https://openalex.org/W2159202424","https://openalex.org/W2170256193","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2535255545","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2610674366","https://openalex.org/W2626544737","https://openalex.org/W2734774145","https://openalex.org/W2767832833","https://openalex.org/W2804644188","https://openalex.org/W2890111732","https://openalex.org/W2891405874","https://openalex.org/W2962701080","https://openalex.org/W2962715207","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963551828","https://openalex.org/W3015199127","https://openalex.org/W3020724926","https://openalex.org/W3026111682","https://openalex.org/W3031404175","https://openalex.org/W3041647828","https://openalex.org/W3096893582","https://openalex.org/W3160903688","https://openalex.org/W3162698503","https://openalex.org/W3163114796","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3186221976","https://openalex.org/W3217000580","https://openalex.org/W4200529817","https://openalex.org/W4206215724","https://openalex.org/W4225281800","https://openalex.org/W6631190155","https://openalex.org/W6680012447","https://openalex.org/W6684458083","https://openalex.org/W6712656540","https://openalex.org/W6731370813","https://openalex.org/W6743446608","https://openalex.org/W6751512325","https://openalex.org/W6758718679","https://openalex.org/W6772886038","https://openalex.org/W6774995033"],"related_works":["https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2081900870","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W2953716828","https://openalex.org/W2469820710"],"abstract_inverted_index":{"Speech":[0],"separation":[1,127,248],"has":[2],"been":[3,27,46],"employed":[4],"in":[5,112,177,182],"important":[6,110],"applications":[7],"such":[8,48],"as":[9,49,64,122],"automatic":[10],"speech,":[11],"paralinguistics,":[12],"speech":[13,31],"recognition,":[14],"hearing":[15],"aids,":[16],"and":[17,32,75,141,160,236,255,276,302,312],"human-machine":[18],"interactions.":[19],"In":[20,52,149,292],"recent":[21],"years,":[22],"deep":[23,50,61,76],"neural":[24],"networks":[25],"have":[26,45],"widely":[28],"used":[29,84,121],"for":[30,99,125,146],"music":[33],"separation.":[34],"Some":[35],"of":[36,190,203],"these":[37],"breakthrough":[38],"successful":[39],"models":[40],"based":[41],"on":[42,252,288,309],"embedding":[43,169],"vectors":[44,162],"proposed,":[47],"clustering.":[51],"this":[53],"paper,":[54],"we":[55,151],"propose":[56],"a":[57,80,94,153],"node":[58,72,81],"encoder":[59,82],"Squash-norm":[60,198],"clustering":[62,77,139,217],"(ESDC)":[63],"an":[65,109,213],"enhanced":[66],"discriminative":[67],"learning":[68,97],"framework":[69],"by":[70,216],"combining":[71],"encoder,":[73],"Squash-norm,":[74,156],"(DC).":[78],"First,":[79],"is":[83],"to":[85,157,163,194,211,244],"create":[86],"intermediate":[87,105,117],"features.":[88],"Node":[89],"encoders":[90],"are":[91,119,187],"developed":[92],"through":[93,137],"matrix":[95],"factorization-based":[96],"method":[98,140],"graph":[100],"representations.":[101],"It":[102],"creates":[103],"distinguishable":[104],"features":[106,118,124],"that":[107],"play":[108],"role":[111],"improving":[113],"performance.":[114],"These":[115],"discriminated":[116],"then":[120],"input":[123,159,179,196],"the":[126,134,138,143,158,165,175,178,191,195,201,204,209,218,222,245,253,259,285,289,295,306,310],"block.":[128],"The":[129],"decoder":[130],"block":[131],"finally":[132],"constructs":[133],"estimation":[135],"mask":[136,215],"reconstructs":[142],"estimated":[144,214],"signal":[145],"each":[147],"source.":[148],"particular,":[150],"apply":[152],"normalization":[154],"function,":[155],"output":[161,205,219],"enhance":[164],"distinction":[166],"between":[167],"high-dimensional":[168],"vectors.":[170,192],"This":[171],"nonlinear":[172],"function":[173],"amplifies":[174],"differences":[176],"vectors,":[180],"resulting":[181],"highly":[183],"unique":[184],"features,":[185],"which":[186],"scalar":[188],"products":[189],"Similar":[193],"vector,":[197,206],"also":[199],"enhances":[200],"discrimination":[202],"thereby":[207],"enhancing":[208],"ability":[210],"construct":[212],"vector.":[220],"Overall,":[221],"proposed":[223,263,296],"ESDC":[224,264,297],"achieves":[225,265],"1.27":[226],"–":[227,232,238,267,272,278],"2.09":[228],"dB":[229,234,240,269,274,280],"SDR,":[230,270],"1.28":[231],"2.21":[233],"SDRi,":[235,275],"1.3":[237],"2.44":[239],"SI-SNRi":[241,281],"gain":[242,282],"compared":[243,283],"DC":[246,286,307],"baseline":[247,287],"performance":[249],"across":[250],"genders":[251],"TSP":[254,311],"TIMIT":[256,290,313],"datasets.":[257,314],"With":[258],"same":[260],"gender,":[261],"our":[262],"1.14":[266],"2.71":[268],"0.99":[271],"2.74":[273],"0.62":[277],"2.86":[279],"with":[284],"dataset.":[291],"all":[293],"cases,":[294],"model":[298],"consistently":[299],"maintains":[300],"STOI":[301],"PESQ":[303],"higher":[304],"than":[305],"baselines":[308]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}