{"id":"https://openalex.org/W2962728945","doi":"https://doi.org/10.1109/mlsp.2017.8168152","title":"Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant training","display_name":"Joint separation and denoising of noisy multi-talker speech using recurrent neural networks and permutation invariant training","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2962728945","doi":"https://doi.org/10.1109/mlsp.2017.8168152","mag":"2962728945"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2017.8168152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5006420917","display_name":"Morten Kolb\u00e6k","orcid":"https://orcid.org/0000-0002-2561-4960"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Morten Kolbaek","raw_affiliation_strings":["Aalborg Universitet, Aalborg, DK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aalborg Universitet, Aalborg, DK","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090108098","display_name":"Zheng\u2010Hua Tan","orcid":"https://orcid.org/0000-0001-6856-8928"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Zheng-Hua Tan","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101679595","display_name":"Jesper Jensen","orcid":"https://orcid.org/0000-0003-1478-622X"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Jensen","raw_affiliation_strings":["Department of Electronic Systems, Aalborg University, Aalborg, Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7297641038894653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7215058207511902},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6047623157501221},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5700770616531372},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5113574862480164},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5062100291252136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4970071613788605},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.49368080496788025},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.452831506729126},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.45066678524017334},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4331081211566925},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4251425266265869},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.42358261346817017},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3195618987083435}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7297641038894653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7215058207511902},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6047623157501221},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5700770616531372},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5113574862480164},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5062100291252136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4970071613788605},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.49368080496788025},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.452831506729126},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.45066678524017334},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4331081211566925},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4251425266265869},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.42358261346817017},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3195618987083435},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2017.8168152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1635512741","https://openalex.org/W1790748249","https://openalex.org/W1893876709","https://openalex.org/W1971168548","https://openalex.org/W2046869671","https://openalex.org/W2064675550","https://openalex.org/W2069681747","https://openalex.org/W2087368178","https://openalex.org/W2094461119","https://openalex.org/W2109215269","https://openalex.org/W2127851351","https://openalex.org/W2144763279","https://openalex.org/W2181607856","https://openalex.org/W2221409856","https://openalex.org/W2289394825","https://openalex.org/W2364134690","https://openalex.org/W2460742184","https://openalex.org/W2515930231","https://openalex.org/W2516001803","https://openalex.org/W2533523411","https://openalex.org/W2550397165","https://openalex.org/W2557738935","https://openalex.org/W2558539285","https://openalex.org/W2558649592","https://openalex.org/W2581082771","https://openalex.org/W2734774145","https://openalex.org/W2765425905","https://openalex.org/W2962715207","https://openalex.org/W2963266252","https://openalex.org/W3124666641","https://openalex.org/W3124794156","https://openalex.org/W3127686677","https://openalex.org/W4253928870","https://openalex.org/W6662385463","https://openalex.org/W6688843265","https://openalex.org/W6789284391"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2092735486","https://openalex.org/W2156376969","https://openalex.org/W2117416982","https://openalex.org/W2002243964"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,22,133,172,198],"propose":[4],"to":[5,208],"use":[6],"utterance-level":[7],"Permutation":[8],"Invariant":[9],"Training":[10],"(uPIT)":[11],"for":[12,36,124],"speaker":[13,38,116],"independent":[14,39,117],"multi-talker":[15,40,118],"speech":[16,41,119],"separation":[17,42,120],"and":[18,50,60,80,121,128,143,152,183],"denoising,":[19],"simultaneously.":[20],"Specifically,":[21,132],"train":[23],"deep":[24,88],"bi-directional":[25,89],"Long":[26],"Short-Term":[27],"Memory":[28],"(LSTM)":[29],"Recurrent":[30],"Neural":[31],"Networks":[32],"(RNNs)":[33],"using":[34,93,148,204],"uPIT,":[35],"single-channel":[37],"in":[43,75,95,169],"multiple":[44,161],"noisy":[45,96,185],"conditions,":[46],"including":[47],"both":[48,181],"synthetic":[49],"real-life":[51],"noise":[52,61,78,126,150,162,209],"signals.":[53],"We":[54,85],"focus":[55],"our":[56],"experiments":[57],"on":[58,67,114],"generalizability":[59],"robustness":[62],"of":[63,70,77,82,159,195],"models":[64],"that":[65,87,136,153,174,200],"rely":[66],"various":[68,125],"types":[69,127,163,210],"a":[71,154,166,175,188],"priori":[72,189],"knowledge":[73,190],"e.g.":[74],"terms":[76],"type":[79],"number":[81,194],"simultaneous":[83],"speakers.":[84,196],"show":[86,135,173,199],"LSTM":[90,137,177,201],"RNNs":[91,138,202],"trained":[92,203],"uPIT":[94,205],"environments":[97],"can":[98,139,179],"improve":[99],"the":[100,107,115,192],"Signal-to-Distortion":[101],"Ratio":[102],"(SDR)":[103],"as":[104,106],"well":[105,207],"Extended":[108],"Short-Time":[109],"Objective":[110],"Intelligibility":[111],"(ESTOI)":[112],"measure,":[113],"denoising":[122],"task,":[123],"Signal-to-Noise":[129],"Ratios":[130],"(SNRs).":[131],"first":[134],"achieve":[140],"large":[141],"SDR":[142],"ESTOI":[144],"improvements,":[145],"when":[146],"evaluated":[147],"known":[149],"types,":[151],"single":[155,176],"model":[156],"is":[157],"capable":[158],"handling":[160],"with":[164],"only":[165],"slight":[167],"decrease":[168],"performance.":[170],"Furthermore,":[171],"RNN":[178],"handle":[180],"two-speaker":[182],"three-speaker":[184],"mixtures,":[186],"without":[187],"about":[191],"exact":[193],"Finally,":[197],"generalize":[206],"not":[211],"seen":[212],"during":[213],"training.":[214]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}