{"id":"https://openalex.org/W2785860907","doi":"https://doi.org/10.1109/apsipa.2017.8282020","title":"Speech separation by cost-sensitive deep learning","display_name":"Speech separation by cost-sensitive deep learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2785860907","doi":"https://doi.org/10.1109/apsipa.2017.8282020","mag":"2785860907"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-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/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao-Lei Zhang","raw_affiliation_strings":["Center for Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Center for Intelligent Acoustics and Immersive Communications, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100450091"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.5548,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.67791348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"162"},"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":0.9991000294685364,"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":0.9990000128746033,"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":0.8114579916000366},{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.7750433087348938},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6434752345085144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6114041805267334},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.5280600190162659},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.525345504283905},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4553338885307312},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.42065513134002686},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41067618131637573},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34329402446746826},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.08364823460578918},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07072070240974426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114579916000366},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.7750433087348938},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6434752345085144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114041805267334},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.5280600190162659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.525345504283905},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4553338885307312},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.42065513134002686},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41067618131637573},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34329402446746826},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.08364823460578918},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07072070240974426},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1790748249","https://openalex.org/W2017608047","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2119191234","https://openalex.org/W2168379380","https://openalex.org/W2197404611","https://openalex.org/W2291877678","https://openalex.org/W2304609584","https://openalex.org/W2626775259","https://openalex.org/W2962866211","https://openalex.org/W6637992904","https://openalex.org/W6662018355","https://openalex.org/W6668037159","https://openalex.org/W6684924409","https://openalex.org/W6739898779","https://openalex.org/W6743462201"],"related_works":["https://openalex.org/W2775065021","https://openalex.org/W2963390466","https://openalex.org/W2798953195","https://openalex.org/W2797110164","https://openalex.org/W3119238434","https://openalex.org/W2405919102","https://openalex.org/W2783984851","https://openalex.org/W2994882344","https://openalex.org/W3147966746","https://openalex.org/W3048266820","https://openalex.org/W3010327795","https://openalex.org/W2997299525","https://openalex.org/W2807374857","https://openalex.org/W2067181967","https://openalex.org/W2777864948","https://openalex.org/W2890820256","https://openalex.org/W84880661","https://openalex.org/W3158205601","https://openalex.org/W2606806821","https://openalex.org/W2962959469"],"abstract_inverted_index":{"Deep":[0],"learning":[1,91,110,116,125,146],"based":[2],"speech":[3,98],"separation":[4,99],"has":[5],"demonstrated":[6],"good":[7,27,45],"performance":[8,76,96],"in":[9,29,63,74],"adverse":[10],"environments.":[11],"Recent":[12],"study":[13],"shows":[14,26],"that":[15],"multi-condition":[16],"training,":[17],"which":[18,72,104],"trains":[19],"a":[20,44,56,75,112,141],"model":[21],"with":[22,36,111,117,126],"several":[23],"noise":[24,34],"scenarios,":[25],"generalization":[28],"test.":[30],"However,":[31],"treating":[32],"all":[33],"scenarios":[35],"the":[37,61,95,106,137,151,154],"same":[38],"training":[39,53,70,121,130],"cost":[40],"is":[41,50],"usually":[42],"not":[43],"choice:":[46],"A":[47],"common":[48],"problem":[49],"that,":[51],"when":[52,78],"data":[54,62],"contain":[55],"wide":[57],"range":[58],"of":[59,97,108,120,129,153],"SNR,":[60],"low":[64,102],"SNR":[65],"environments":[66],"suffer":[67],"from":[68],"large":[69],"loss,":[71],"results":[73,149],"drop":[77],"test":[79],"SNRs":[80],"are":[81,105],"low.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86],"propose":[87,134],"three":[88,138],"cost-sensitive":[89,113,118,127],"deep":[90,144],"methods":[92,100,107,139],"to":[93,135,140],"improve":[94],"at":[101],"SNRs,":[103],"(i)":[109],"objective,":[114],"(ii)":[115],"oversampling":[119],"data,":[122],"and":[123],"(iii)":[124],"undersampling":[128],"data.":[131],"We":[132],"also":[133],"aggregate":[136],"cost-":[142],"sensitive":[143],"ensemble":[145],"method.":[147],"Experimental":[148],"demonstrate":[150],"effectiveness":[152],"proposed":[155],"methods.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}