{"id":"https://openalex.org/W2069681747","doi":"https://doi.org/10.1109/taslp.2014.2352935","title":"On Training Targets for Supervised Speech Separation","display_name":"On Training Targets for Supervised Speech Separation","publication_year":2014,"publication_date":"2014-08-28","ids":{"openalex":"https://openalex.org/W2069681747","doi":"https://doi.org/10.1109/taslp.2014.2352935","mag":"2069681747","pmid":"https://pubmed.ncbi.nlm.nih.gov/25599083"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2352935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2352935","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/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, The Ohio State University, Columbus, OH 43210 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210 USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH","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 and Brain Sciences, The Ohio State University, Columbus, OH 43210 USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH 43210 USA","institution_ids":[]},{"raw_affiliation_string":"Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH#TAB#","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101664515"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":43.252,"has_fulltext":false,"cited_by_count":1119,"citation_normalized_percentile":{"value":0.99920178,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"22","issue":"12","first_page":"1849","last_page":"1858"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9983999729156494,"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":0.7415506839752197},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.712959349155426},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6319905519485474},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6029260754585266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5500577092170715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5144715309143066},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4584483802318573},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.45162808895111084},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.45017409324645996},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3030366599559784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1901710033416748},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1776764690876007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.170719712972641}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7415506839752197},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.712959349155426},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6319905519485474},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6029260754585266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5500577092170715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5144715309143066},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4584483802318573},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.45162808895111084},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.45017409324645996},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3030366599559784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1901710033416748},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1776764690876007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.170719712972641},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2014.2352935","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2352935","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:25599083","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25599083","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":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:europepmc.org:3261481","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4293540","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1495679096","https://openalex.org/W1525463183","https://openalex.org/W1552314771","https://openalex.org/W1635512741","https://openalex.org/W1814328102","https://openalex.org/W1904365287","https://openalex.org/W1963970749","https://openalex.org/W1974387177","https://openalex.org/W1979099822","https://openalex.org/W1989364685","https://openalex.org/W1999736059","https://openalex.org/W2013608223","https://openalex.org/W2027701650","https://openalex.org/W2027804983","https://openalex.org/W2042750879","https://openalex.org/W2047919706","https://openalex.org/W2052667477","https://openalex.org/W2057200980","https://openalex.org/W2057889776","https://openalex.org/W2068144845","https://openalex.org/W2073612610","https://openalex.org/W2078528584","https://openalex.org/W2079362249","https://openalex.org/W2085191029","https://openalex.org/W2086139506","https://openalex.org/W2087126002","https://openalex.org/W2109215269","https://openalex.org/W2119901478","https://openalex.org/W2122982914","https://openalex.org/W2131753991","https://openalex.org/W2138939691","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2144786298","https://openalex.org/W2146502635","https://openalex.org/W2147455188","https://openalex.org/W2165899180","https://openalex.org/W2168379380","https://openalex.org/W2539207221","https://openalex.org/W3127686677","https://openalex.org/W4245919820","https://openalex.org/W6638523313","https://openalex.org/W6640036494","https://openalex.org/W6680324615","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2900450731"],"abstract_inverted_index":{"Formulation":[0],"of":[1,39,42,56,75,145,188],"speech":[2,61,181,190],"separation":[3,85],"as":[4,52],"a":[5,17,22,30,36],"supervised":[6,18,65,189],"learning":[7,19,66],"problem":[8],"has":[9],"shown":[10],"considerable":[11],"promise.":[12],"In":[13,78,151],"its":[14,57,111],"simplest":[15],"form,":[16],"algorithm,":[20],"typically":[21],"deep":[23],"neural":[24],"network,":[25],"is":[26,50,69],"trained":[27],"to":[28,35,72],"learn":[29],"mapping":[31],"from":[32],"noisy":[33],"features":[34],"time-frequency":[37],"representation":[38],"the":[40,45,53,73,93,95,99,104,116,129,134,137,140],"target":[41,54,96],"interest.":[43],"Traditionally,":[44],"ideal":[46,100],"binary":[47,76,97],"mask":[48,102,113,132],"(IBM)":[49],"used":[51],"because":[55],"simplicity":[58],"and":[59,83,110,115,136,148,180],"large":[60],"intelligibility":[62,147],"gains.":[63],"The":[64],"framework,":[67],"however,":[68],"not":[70],"restricted":[71],"use":[74],"targets.":[77,168],"this":[79],"study,":[80],"we":[81,153],"evaluate":[82],"compare":[84],"results":[86,122],"by":[87],"using":[88],"different":[89],"training":[90],"targets,":[91,133,158],"including":[92],"IBM,":[94],"mask,":[98],"ratio":[101,131],"(IRM),":[103],"short-time":[105],"Fourier":[106],"transform":[107],"spectral":[108,165],"magnitude":[109],"corresponding":[112],"(FFT-MASK),":[114],"Gammatone":[117],"frequency":[118],"power":[119],"spectrum.":[120],"Our":[121],"in":[123,143,159,176],"various":[124],"test":[125],"conditions":[126],"reveal":[127],"that":[128,155],"two":[130],"IRM":[135],"FFT-MASK,":[138],"outperform":[139],"other":[141],"targets":[142],"terms":[144],"objective":[146],"quality":[149],"metrics.":[150],"addition,":[152],"find":[154],"masking":[156],"based":[157,167],"general,":[160],"are":[161],"significantly":[162],"better":[163],"than":[164],"envelope":[166],"We":[169],"also":[170],"present":[171],"comparisons":[172],"with":[173],"recent":[174],"methods":[175],"non-negative":[177],"matrix":[178],"factorization":[179],"enhancement,":[182],"which":[183],"show":[184],"clear":[185],"performance":[186],"advantages":[187],"separation.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":51},{"year":2024,"cited_by_count":68},{"year":2023,"cited_by_count":103},{"year":2022,"cited_by_count":119},{"year":2021,"cited_by_count":148},{"year":2020,"cited_by_count":202},{"year":2019,"cited_by_count":142},{"year":2018,"cited_by_count":127},{"year":2017,"cited_by_count":75},{"year":2016,"cited_by_count":39},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}