{"id":"https://openalex.org/W2698117193","doi":"https://doi.org/10.1109/icassp.2017.7952120","title":"Recurrent deep stacking networks for supervised speech separation","display_name":"Recurrent deep stacking networks for supervised speech separation","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2698117193","doi":"https://doi.org/10.1109/icassp.2017.7952120","mag":"2698117193"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"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":"Zhong-Qiu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, 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":["Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.8100055456161499},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6134757995605469},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5853833556175232},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5685908198356628},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5621323585510254},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5499007701873779},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5330637097358704},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5078838467597961},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5016465187072754},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49366292357444763},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.47779613733291626},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.47319599986076355},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4477071762084961},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44088321924209595},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34042418003082275}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100055456161499},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6134757995605469},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5853833556175232},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5685908198356628},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621323585510254},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5499007701873779},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5330637097358704},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5078838467597961},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5016465187072754},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49366292357444763},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.47779613733291626},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.47319599986076355},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4477071762084961},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44088321924209595},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34042418003082275},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952120","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1790748249","https://openalex.org/W1836465849","https://openalex.org/W1897240248","https://openalex.org/W2006129368","https://openalex.org/W2035576074","https://openalex.org/W2044893557","https://openalex.org/W2046869671","https://openalex.org/W2069681747","https://openalex.org/W2108597378","https://openalex.org/W2141411743","https://openalex.org/W2148575186","https://openalex.org/W2168379380","https://openalex.org/W2176412452","https://openalex.org/W2194775991","https://openalex.org/W2243290847","https://openalex.org/W2288645994","https://openalex.org/W2291652038","https://openalex.org/W2291877678","https://openalex.org/W2296167893","https://openalex.org/W2304609584","https://openalex.org/W2344535577","https://openalex.org/W2396918387","https://openalex.org/W2398264106","https://openalex.org/W2400339399","https://openalex.org/W2405589348","https://openalex.org/W2460742184","https://openalex.org/W2515930231","https://openalex.org/W2517616541","https://openalex.org/W2561557072","https://openalex.org/W2635471793","https://openalex.org/W2718052359","https://openalex.org/W2755891984","https://openalex.org/W2949117887","https://openalex.org/W2962949994","https://openalex.org/W2963285578","https://openalex.org/W3124794156","https://openalex.org/W4212863985","https://openalex.org/W4233392025","https://openalex.org/W6712395177","https://openalex.org/W6713519970","https://openalex.org/W6744261651"],"related_works":["https://openalex.org/W2035329725","https://openalex.org/W4376641153","https://openalex.org/W2050788868","https://openalex.org/W4241625287","https://openalex.org/W4250391473","https://openalex.org/W4302292679","https://openalex.org/W2956222435","https://openalex.org/W2027634686","https://openalex.org/W2952283344","https://openalex.org/W4295885776"],"abstract_inverted_index":{"Supervised":[0],"speech":[1,21],"separation":[2],"algorithms":[3],"seldom":[4],"utilize":[5],"output":[6,25],"patterns.":[7],"This":[8],"study":[9],"proposes":[10],"a":[11,67,83,137],"novel":[12],"recurrent":[13,68,138],"deep":[14,84,90],"stacking":[15],"approach":[16],"for":[17,152],"time-frequency":[18],"masking":[19],"based":[20],"separation,":[22],"where":[23],"the":[24,32,43,56,59,96,103,112,121,124,128,131,146,156,161],"context":[26],"is":[27,40,73],"explicitly":[28],"employed":[29],"to":[30,41,53,77,81,119,144],"improve":[31],"accuracy":[33],"of":[34,46,58,95,105,163],"mask":[35,57],"estimation.":[36],"The":[37,92],"key":[38],"idea":[39],"incorporate":[42],"estimated":[44,93,114],"masks":[45,94,115],"several":[47],"previous":[48,97],"frames":[49,98],"as":[50,66],"additional":[51,117],"inputs":[52,118],"better":[54],"estimate":[55],"current":[60],"frame.":[61],"Rather":[62],"than":[63],"formulating":[64],"it":[65],"neural":[69,85],"network":[70,86],"(RNN),":[71],"which":[72],"potentially":[74],"much":[75],"harder":[76],"train,":[78],"we":[79,142],"propose":[80,143],"train":[82,120],"(DNN)":[87],"with":[88],"implicit":[89],"stacking.":[91],"are":[99],"updated":[100,113],"only":[101],"at":[102],"end":[104],"each":[106],"DNN":[107,122,132],"training":[108],"epoch,":[109],"and":[110],"then":[111],"provide":[116],"in":[123,136],"next":[125],"epoch.":[126],"At":[127],"test":[129],"stage,":[130],"makes":[133],"predictions":[134],"sequentially":[135],"fashion.":[139],"In":[140],"addition,":[141],"use":[145],"L":[147],"<sub":[148],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sub>":[150],"loss":[151],"training.":[153],"Experiments":[154],"on":[155],"CHiME-2":[157],"(task-2)":[158],"dataset":[159],"demonstrate":[160],"effectiveness":[162],"our":[164],"proposed":[165],"approach.":[166]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}