{"id":"https://openalex.org/W2944204429","doi":"https://doi.org/10.1109/iscslp.2018.8706621","title":"Convolutional Neural Turing Machine for Speech Separation","display_name":"Convolutional Neural Turing Machine for Speech Separation","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944204429","doi":"https://doi.org/10.1109/iscslp.2018.8706621","mag":"2944204429"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/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, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","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, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, National Chiao Tung University, 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":0.1662,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51336375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"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":0.9984999895095825,"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/T11447","display_name":"Blind Source Separation Techniques","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":0.8264998197555542},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.6930805444717407},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5841995477676392},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5477844476699829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4618799388408661},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4254450798034668},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.421790212392807},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40794435143470764},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33181482553482056},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12037679553031921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264998197555542},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.6930805444717407},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5841995477676392},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5477844476699829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4618799388408661},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4254450798034668},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.421790212392807},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40794435143470764},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33181482553482056},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12037679553031921}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1522301498","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/W2141411743","https://openalex.org/W2146544734","https://openalex.org/W2183821610","https://openalex.org/W2242047860","https://openalex.org/W2401638432","https://openalex.org/W2404724332","https://openalex.org/W2405589348","https://openalex.org/W2515930231","https://openalex.org/W2749679082","https://openalex.org/W2771697229","https://openalex.org/W2804644188","https://openalex.org/W2891462019","https://openalex.org/W2950527759","https://openalex.org/W2951008357","https://openalex.org/W2964121744","https://openalex.org/W3033736971","https://openalex.org/W4303633609","https://openalex.org/W6631190155","https://openalex.org/W6638318767","https://openalex.org/W6638545294","https://openalex.org/W6684821475","https://openalex.org/W6712931226","https://openalex.org/W6713519970","https://openalex.org/W6732742072","https://openalex.org/W6743570848","https://openalex.org/W6745960141"],"related_works":["https://openalex.org/W2036157531","https://openalex.org/W2056406069","https://openalex.org/W1974981856","https://openalex.org/W1518859147","https://openalex.org/W2401567014","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Long":[0],"short-term":[1,178],"memory":[2,50,103,145,149],"(LSTM)":[3],"has":[4],"been":[5],"successfully":[6],"developed":[7],"for":[8,155,172],"monaural":[9],"speech":[10,157,173],"separation.":[11],"Temporal":[12],"information":[13,58],"is":[14,38,120,131,153],"learned":[15],"by":[16],"using":[17],"dynamic":[18],"states":[19],"which":[20,119],"are":[21,44,96],"evolved":[22],"through":[23],"time":[24,106],"and":[25,66,98,138,143,169],"stored":[26],"as":[27,40],"an":[28,101],"internal":[29,49],"memory.":[30],"The":[31,148],"spectro-temporal":[32,94,113],"data":[33,95],"matrix":[34],"of":[35,93,164,177],"mixed":[36],"signal":[37],"flattened":[39,71],"input":[41],"vectors.":[42],"There":[43],"twofold":[45],"limitations.":[46],"First,":[47],"the":[48,63,70,90,112,124,136,162],"in":[51,69,100,115,175],"LSTM":[52,171],"could":[53],"not":[54],"sufficiently":[55],"characterize":[56],"long-term":[57],"from":[59],"different":[60],"sources.":[61],"Second,":[62],"temporal":[64],"correlation":[65],"frequency":[67],"neighboring":[68],"vectors":[72],"were":[73],"smeared.":[74],"To":[75],"deal":[76],"with":[77],"these":[78],"limitations,":[79],"this":[80],"paper":[81],"presents":[82],"a":[83],"convolutional":[84,170],"neural":[85],"Turing":[86],"machine":[87],"(ConvNTM)":[88],"where":[89],"feature":[91],"maps":[92],"extracted":[97],"embedded":[99],"external":[102],"at":[104],"each":[105],"step.":[107],"ConvNTM":[108,165],"aims":[109],"to":[110,122,133,141,166],"preserve":[111],"structure":[114],"long":[116],"sequential":[117],"signals":[118],"exploited":[121],"estimate":[123],"separated":[125],"spectral":[126],"signals.":[127],"An":[128],"addressing":[129],"mechanism":[130],"introduced":[132],"continuously":[134],"calculate":[135],"read":[137],"write":[139],"heads":[140],"retrieve":[142],"update":[144],"slots,":[146],"respectively.":[147],"augmented":[150],"source":[151],"separation":[152],"implemented":[154],"single-channel":[156],"enhancement.":[158],"Experimental":[159],"results":[160],"illustrate":[161],"superiority":[163],"LSTM,":[167],"NTM":[168],"enhancement":[174],"terms":[176],"objective":[179],"intelligibility":[180],"measure.":[181]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}