{"id":"https://openalex.org/W2771697229","doi":"https://doi.org/10.1109/mlsp.2017.8168120","title":"Memory augmented neural network for source separation","display_name":"Memory augmented neural network for source separation","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2771697229","doi":"https://doi.org/10.1109/mlsp.2017.8168120","mag":"2771697229"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp.2017.8168120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168120","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/A5112434805","display_name":"Kai-Wei Tsou","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Wei Tsou","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9986000061035156,"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":0.8076623678207397},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8009245991706848},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6544462442398071},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6296514272689819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.509454071521759},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.49434709548950195},{"id":"https://openalex.org/keywords/auxiliary-memory","display_name":"Auxiliary memory","score":0.44955217838287354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4194106161594391},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41466203331947327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076623678207397},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8009245991706848},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6544462442398071},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6296514272689819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.509454071521759},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.49434709548950195},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.44955217838287354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4194106161594391},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41466203331947327},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp.2017.8168120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp.2017.8168120","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1793121960","https://openalex.org/W1815076433","https://openalex.org/W2031647436","https://openalex.org/W2064675550","https://openalex.org/W2078528584","https://openalex.org/W2113907273","https://openalex.org/W2130942839","https://openalex.org/W2141411743","https://openalex.org/W2146544734","https://openalex.org/W2183821610","https://openalex.org/W2404724332","https://openalex.org/W2405589348","https://openalex.org/W2515930231","https://openalex.org/W2749679082","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W4303633609","https://openalex.org/W6607333740","https://openalex.org/W6638318767","https://openalex.org/W6638545294","https://openalex.org/W6679436768","https://openalex.org/W6713519970"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W2109916967","https://openalex.org/W2890297197","https://openalex.org/W2101697354","https://openalex.org/W1538193578","https://openalex.org/W3206636855","https://openalex.org/W1538606284","https://openalex.org/W2373874059"],"abstract_inverted_index":{"Recurrent":[0],"neural":[1,80,91,123,130],"network":[2,81,124,131],"(RNN)":[3],"based":[4,119],"on":[5,120],"long":[6],"short-term":[7,137],"memory":[8,50,71,78,121],"(LSTM)":[9],"has":[10],"been":[11],"successfully":[12],"developed":[13],"for":[14,82,99],"single-channel":[15],"source":[16,40,83],"separation.":[17,84],"Temporal":[18],"information":[19],"is":[20,42],"learned":[21],"by":[22,67],"using":[23,128],"dynamic":[24],"states":[25],"which":[26,51],"are":[27],"evolved":[28],"through":[29],"time":[30],"and":[31,74,104,111,132],"stored":[32],"as":[33],"an":[34,69],"internal":[35,49],"memory.":[36],"The":[37],"performance":[38],"of":[39,48,102,108,136],"separation":[41,97],"constrained":[43],"due":[44],"to":[45,94],"the":[46],"limitation":[47,66],"could":[52],"not":[53],"sufficiently":[54],"preserve":[55],"long-term":[56],"characteristics":[57],"from":[58],"different":[59,109],"sources.":[60],"This":[61],"study":[62],"deals":[63],"with":[64],"this":[65],"incorporating":[68],"external":[70],"in":[72,106,134],"RNN":[73],"accordingly":[75],"presents":[76],"a":[77,90,96],"augmented":[79,122],"In":[85],"particular,":[86],"we":[87],"carry":[88],"out":[89],"Turing":[92],"machine":[93],"learn":[95],"model":[98],"sequential":[100],"signals":[101],"speech":[103,117],"noise":[105,112],"presence":[107],"speakers":[110],"types.":[113],"Experiments":[114],"show":[115],"that":[116,127],"enhancement":[118],"consistently":[125],"outperforms":[126],"deep":[129],"LSTM":[133],"terms":[135],"objective":[138],"intelligibility":[139],"measure.":[140]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}