{"id":"https://openalex.org/W2168379380","doi":"https://doi.org/10.1109/tasl.2013.2250961","title":"Towards Scaling Up Classification-Based Speech Separation","display_name":"Towards Scaling Up Classification-Based Speech Separation","publication_year":2013,"publication_date":"2013-03-22","ids":{"openalex":"https://openalex.org/W2168379380","doi":"https://doi.org/10.1109/tasl.2013.2250961","mag":"2168379380"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2250961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2250961","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Audio, Speech, and Language Processing","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/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"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":true,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, 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":["Department of Computer Science and Engineering and the Center for Cognitive Science, Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive Science, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101664515"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":29.2983,"has_fulltext":false,"cited_by_count":456,"citation_normalized_percentile":{"value":0.99820944,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"21","issue":"7","first_page":"1381","last_page":"1390"},"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":0.9993000030517578,"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":0.9993000030517578,"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/discriminative-model","display_name":"Discriminative model","score":0.7285192012786865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.703820526599884},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7035500407218933},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6431498527526855},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6304525136947632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6122835874557495},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.6054400205612183},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5370022654533386},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5281223058700562},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.523379921913147},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5111318230628967},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49629122018814087},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48714348673820496},{"id":"https://openalex.org/keywords/kernel-method","display_name":"Kernel method","score":0.48616287112236023},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.45361873507499695},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44872090220451355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4315434694290161},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.41135311126708984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15305599570274353}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7285192012786865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.703820526599884},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7035500407218933},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6431498527526855},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6304525136947632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122835874557495},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.6054400205612183},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5370022654533386},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5281223058700562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.523379921913147},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5111318230628967},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49629122018814087},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48714348673820496},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.48616287112236023},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.45361873507499695},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44872090220451355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4315434694290161},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.41135311126708984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15305599570274353},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tasl.2013.2250961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2250961","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.368.2355","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.368.2355","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.ohio-state.edu/~dwang/papers/Wang-Wang.taslp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1618905105","https://openalex.org/W1635512741","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1979099822","https://openalex.org/W1981755271","https://openalex.org/W1989364685","https://openalex.org/W1993882792","https://openalex.org/W2012204351","https://openalex.org/W2013312573","https://openalex.org/W2034040413","https://openalex.org/W2039844283","https://openalex.org/W2057889776","https://openalex.org/W2072128103","https://openalex.org/W2085191029","https://openalex.org/W2100495367","https://openalex.org/W2106525014","https://openalex.org/W2113651538","https://openalex.org/W2115129089","https://openalex.org/W2116064496","https://openalex.org/W2118585731","https://openalex.org/W2118858186","https://openalex.org/W2121973264","https://openalex.org/W2122982914","https://openalex.org/W2128653836","https://openalex.org/W2130325614","https://openalex.org/W2131753991","https://openalex.org/W2135106139","https://openalex.org/W2136922672","https://openalex.org/W2137617983","https://openalex.org/W2138857742","https://openalex.org/W2138939691","https://openalex.org/W2140833774","https://openalex.org/W2142623206","https://openalex.org/W2145759598","https://openalex.org/W2147768505","https://openalex.org/W2148577181","https://openalex.org/W2150866759","https://openalex.org/W2152708632","https://openalex.org/W2153635508","https://openalex.org/W2159202424","https://openalex.org/W2184852195","https://openalex.org/W2606321545","https://openalex.org/W2981666567","https://openalex.org/W3147539069","https://openalex.org/W4231109964","https://openalex.org/W4231807801","https://openalex.org/W6636501900","https://openalex.org/W6677106874","https://openalex.org/W6677656871","https://openalex.org/W6677919164","https://openalex.org/W6680272842","https://openalex.org/W6680300913","https://openalex.org/W6680324615","https://openalex.org/W6680887930","https://openalex.org/W6686418764"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Formulating":[0],"speech":[1],"separation":[2,16,30],"as":[3],"a":[4,40,131,137],"binary":[5],"classification":[6],"problem":[7],"has":[8],"been":[9],"shown":[10],"to":[11,48,54,74,86,108,150],"be":[12],"effective.":[13],"While":[14],"good":[15,148],"performance":[17],"is":[18,53,67,128],"achieved":[19],"in":[20,31],"matched":[21],"test":[22,145],"conditions":[23,33,59,135],"using":[24],"kernel":[25,71,111],"support":[26],"vector":[27],"machines":[28,72],"(SVMs),":[29],"unmatched":[32],"involving":[34],"new":[35],"speakers":[36,152],"and":[37,91,98,106,153],"environments":[38],"remains":[39],"big":[41],"challenge.":[42],"A":[43],"simple":[44],"yet":[45],"effective":[46],"method":[47],"cope":[49],"with":[50],"the":[51,61],"mismatch":[52],"include":[55],"many":[56],"different":[57],"acoustic":[58,96,134],"into":[60],"training":[62,66,79],"set.":[63],"However,":[64],"large-scale":[65],"almost":[68],"intractable":[69],"for":[70],"due":[73],"computational":[75],"complexity.":[76],"To":[77],"enable":[78],"on":[80,130,143],"relatively":[81],"large":[82],"datasets,":[83],"we":[84,116],"propose":[85],"learn":[87],"more":[88],"linearly":[89],"separable":[90],"discriminative":[92],"features":[93,97],"from":[94],"raw":[95],"train":[99,109],"linear":[100],"SVMs,":[101],"which":[102],"are":[103],"much":[104],"easier":[105],"faster":[107],"than":[110],"SVMs.":[112],"For":[113],"feature":[114],"learning,":[115],"employ":[117],"standard":[118],"pre-trained":[119],"deep":[120],"neural":[121],"networks":[122],"(DNNs).":[123],"The":[124],"proposed":[125],"DNN-SVM":[126],"system":[127],"trained":[129],"variety":[132],"of":[133,140],"within":[136],"reasonable":[138],"amount":[139],"time.":[141],"Experiments":[142],"various":[144],"mixtures":[146],"demonstrate":[147],"generalization":[149],"unseen":[151],"background":[154],"noises.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":39},{"year":2021,"cited_by_count":53},{"year":2020,"cited_by_count":68},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":55},{"year":2017,"cited_by_count":38},{"year":2016,"cited_by_count":36},{"year":2015,"cited_by_count":24},{"year":2014,"cited_by_count":24},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}