{"id":"https://openalex.org/W2962935966","doi":"https://doi.org/10.1109/icassp.2018.8462116","title":"TaSNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation","display_name":"TaSNet: Time-Domain Audio Separation Network for Real-Time, Single-Channel Speech Separation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2962935966","doi":"https://doi.org/10.1109/icassp.2018.8462116","mag":"2962935966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Luo","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033351155","display_name":"Nima Mesgarani","orcid":"https://orcid.org/0000-0002-2987-759X"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nima Mesgarani","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048439332"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":45.9307,"has_fulltext":false,"cited_by_count":680,"citation_normalized_percentile":{"value":0.99934972,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"700"},"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":0.9991000294685364,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7985795736312866},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6138730645179749},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5855354070663452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5218528509140015},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.48491960763931274},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4625202417373657},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4581524431705475},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.44912999868392944},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.44744873046875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4054383933544159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25298482179641724},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0962759256362915},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08437734842300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985795736312866},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6138730645179749},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5855354070663452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5218528509140015},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.48491960763931274},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4625202417373657},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4581524431705475},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.44912999868392944},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.44744873046875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4054383933544159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25298482179641724},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0962759256362915},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08437734842300415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1790748249","https://openalex.org/W2072599882","https://openalex.org/W2093522043","https://openalex.org/W2127851351","https://openalex.org/W2163202748","https://openalex.org/W2168103112","https://openalex.org/W2189422931","https://openalex.org/W2291877678","https://openalex.org/W2296073425","https://openalex.org/W2302255633","https://openalex.org/W2304609584","https://openalex.org/W2304648132","https://openalex.org/W2398826216","https://openalex.org/W2508048623","https://openalex.org/W2519091744","https://openalex.org/W2519994964","https://openalex.org/W2552071709","https://openalex.org/W2558649592","https://openalex.org/W2567070169","https://openalex.org/W2584032004","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2742004888","https://openalex.org/W2962715207","https://openalex.org/W2963341071","https://openalex.org/W3124794156","https://openalex.org/W3124972797","https://openalex.org/W6698183232","https://openalex.org/W6712560600","https://openalex.org/W6731370813","https://openalex.org/W6742082877"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2386453889","https://openalex.org/W2136112003","https://openalex.org/W2161396743","https://openalex.org/W2520443045","https://openalex.org/W3134790285","https://openalex.org/W1565692302"],"abstract_inverted_index":{"Robust":[0],"speech":[1,8,57,151,159],"processing":[2],"in":[3,27,42,64,99,185],"multi-talker":[4],"environments":[5],"requires":[6],"effective":[7],"separation.":[9,58],"Recent":[10],"deep":[11],"learning":[12],"systems":[13],"have":[14],"made":[15],"significant":[16],"progress":[17],"toward":[18],"solving":[19],"this":[20],"problem,":[21],"yet":[22],"it":[23],"remains":[24],"challenging":[25],"particularly":[26],"real-time,":[28],"short":[29],"latency":[30,167],"applications.":[31],"Most":[32],"methods":[33],"attempt":[34],"to":[35,78,90,127],"construct":[36],"a":[37],"mask":[38],"for":[39,56,175],"each":[40],"source":[41,109,130],"time-frequency":[43,61],"representation":[44,55],"of":[45,129,158,168],"the":[46,97,100,108,118,124,140,145,155,164,169],"mixture":[47],"signal":[48,98],"which":[49,75,135],"is":[50,76,136,181],"not":[51],"necessarily":[52],"an":[53,103],"optimal":[54],"In":[59],"addition,":[60],"decomposition":[62,120],"results":[63],"inherent":[65],"problems":[66],"such":[67,183],"as":[68,184],"phase/magnitude":[69],"decoupling":[70],"and":[71,106,122,149,161,187],"long":[72],"time":[73],"window":[74],"required":[77,166],"achieve":[79],"sufficient":[80],"frequency":[81,119],"resolution.":[82],"We":[83,94],"propose":[84],"Time-domain":[85],"Audio":[86],"Separation":[87],"Network":[88],"(TasNet)":[89],"overcome":[91],"these":[92],"limitations.":[93],"directly":[95],"model":[96],"time-domain":[101],"using":[102],"encoder-decoder":[104],"framework":[105],"perform":[107],"separation":[110,125,152],"on":[111,132],"nonnegative":[112],"encoder":[113,133],"outputs.":[114],"This":[115,171],"method":[116],"removes":[117],"step":[121],"reduces":[123,154,163],"problem":[126],"estimation":[128],"masks":[131],"outputs":[134],"then":[137],"synthesized":[138],"by":[139],"decoder.":[141],"Our":[142],"system":[143],"outperforms":[144],"current":[146],"state-of-the-art":[147],"causal":[148],"noncausal":[150],"algorithms,":[153],"computational":[156],"cost":[157],"separation,":[160],"significantly":[162],"minimum":[165],"output.":[170],"makes":[172],"TasNet":[173],"suitable":[174],"applications":[176],"where":[177],"low-power,":[178],"real-time":[179],"implementation":[180],"desirable":[182],"hearable":[186],"telecommunication":[188],"devices.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":82},{"year":2024,"cited_by_count":87},{"year":2023,"cited_by_count":109},{"year":2022,"cited_by_count":114},{"year":2021,"cited_by_count":113},{"year":2020,"cited_by_count":95},{"year":2019,"cited_by_count":57},{"year":2018,"cited_by_count":12},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}