{"id":"https://openalex.org/W3146854175","doi":"https://doi.org/10.1109/slt48900.2021.9383464","title":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","display_name":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3146854175","doi":"https://doi.org/10.1109/slt48900.2021.9383464","mag":"3146854175"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5102313170","display_name":"Max W. Y. Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Max W. Y. Lam","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5516,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93586396,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"808"},"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":0.9997000098228455,"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":0.9983999729156494,"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":0.8121170401573181},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6916778087615967},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6083254814147949},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5892215371131897},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5569062829017639},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5469413995742798},{"id":"https://openalex.org/keywords/attention-network","display_name":"Attention network","score":0.5137961506843567},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.509755551815033},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4626603424549103},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.45924973487854004},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4524012506008148},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.4520154893398285},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32677918672561646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2294028401374817},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22777026891708374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121170401573181},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6916778087615967},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6083254814147949},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5892215371131897},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5569062829017639},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5469413995742798},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.5137961506843567},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.509755551815033},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4626603424549103},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.45924973487854004},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4524012506008148},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.4520154893398285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32677918672561646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2294028401374817},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22777026891708374},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W855165587","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1899504021","https://openalex.org/W1924770834","https://openalex.org/W1991139021","https://openalex.org/W2095705004","https://openalex.org/W2116261113","https://openalex.org/W2221409856","https://openalex.org/W2405883473","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2792764867","https://openalex.org/W2794209590","https://openalex.org/W2892009249","https://openalex.org/W2896457183","https://openalex.org/W2899771611","https://openalex.org/W2900292050","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2952218014","https://openalex.org/W2956480774","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963452667","https://openalex.org/W2963951265","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2970730223","https://openalex.org/W2972451902","https://openalex.org/W2972460025","https://openalex.org/W2973143779","https://openalex.org/W2973201641","https://openalex.org/W2996969697","https://openalex.org/W2998678989","https://openalex.org/W3004309045","https://openalex.org/W3015199127","https://openalex.org/W3015383493","https://openalex.org/W3015794161","https://openalex.org/W3016129867","https://openalex.org/W3045904949","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3104896896","https://openalex.org/W3144345593","https://openalex.org/W4385245566","https://openalex.org/W6623629580","https://openalex.org/W6631190155","https://openalex.org/W6631636882","https://openalex.org/W6640212811","https://openalex.org/W6674330103","https://openalex.org/W6739901393","https://openalex.org/W6749825310","https://openalex.org/W6751512325","https://openalex.org/W6755207826","https://openalex.org/W6756040250","https://openalex.org/W6763832098","https://openalex.org/W6765571568","https://openalex.org/W6768815455","https://openalex.org/W6769412140","https://openalex.org/W6777478455"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W3017902212","https://openalex.org/W2964335273","https://openalex.org/W1544923983","https://openalex.org/W2787518671"],"abstract_inverted_index":{"Recent":[0],"research":[1],"on":[2,78],"the":[3,22,47,63,67,85,94,97,120,153,156,187],"time-domain":[4],"audio":[5],"separation":[6,134],"networks":[7],"(TasNets)":[8],"has":[9,131,167],"brought":[10],"great":[11],"success":[12],"to":[13,20,93,152],"speech":[14],"separation.":[15],"Nevertheless,":[16],"conventional":[17],"TasNets":[18],"struggle":[19],"satisfy":[21],"memory":[23,145],"and":[24,60,69,104,146],"latency":[25],"constraints":[26],"in":[27,76,159,171,174,186],"industrial":[28],"applications.":[29],"In":[30],"this":[31],"regard,":[32],"we":[33,51],"design":[34],"a":[35,54,90,114,137,160,177],"low-cost":[36],"high-performance":[37],"architecture,":[38],"namely,":[39],"globally":[40],"attentive":[41],"locally":[42],"recurrent":[43],"(GALR)":[44],"network.":[45],"Alike":[46],"dual-path":[48],"RNN":[49],"(DPRNN),":[50],"first":[52],"split":[53],"feature":[55],"sequence":[56,64,95],"into":[57],"2D":[58],"segments":[59],"then":[61],"process":[62],"along":[65,84,96],"both":[66],"intra-":[68],"inter-segment":[70,86,98],"dimensions.":[71],"Our":[72,108],"main":[73],"innovation":[74],"lies":[75],"that,":[77],"top":[79],"of":[80,180,184],"features":[81],"recurrently":[82],"processed":[83],"dimensions,":[87],"GALR":[88,112,166],"applies":[89],"self-attention":[91],"mechanism":[92],"dimension,":[99],"which":[100],"aggregates":[101],"context-aware":[102],"information":[103],"also":[105],"enables":[106],"parallelization.":[107],"experiments":[109],"suggest":[110],"that":[111],"is":[113],"notably":[115],"more":[116],"effective":[117],"network":[118],"than":[119],"prior":[121],"work.":[122],"On":[123,155],"one":[124],"hand,":[125,158],"with":[126,141,164,176],"only":[127],"1.5M":[128],"parameters,":[129],"it":[130],"achieved":[132],"comparable":[133,161],"performance":[135],"at":[136],"much":[138],"lower":[139],"cost":[140],"36.1%":[142],"less":[143],"runtime":[144],"49.4%":[147],"fewer":[148],"computational":[149],"operations,":[150],"relative":[151],"DPRNN.":[154],"other":[157],"model":[162],"size":[163],"DPRNN,":[165],"consistently":[168],"outperformed":[169],"DPRNN":[170],"three":[172],"datasets,":[173],"particular,":[175],"substantial":[178],"margin":[179],"2.4dB":[181],"absolute":[182],"improvement":[183],"SI-SNRi":[185],"benchmark":[188],"WSJ0-2mix":[189],"task.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}