{"id":"https://openalex.org/W4375869299","doi":"https://doi.org/10.1109/icassp49357.2023.10096724","title":"On The Design and Training Strategies for Rnn-Based Online Neural Speech Separation Systems","display_name":"On The Design and Training Strategies for Rnn-Based Online Neural Speech Separation Systems","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869299","doi":"https://doi.org/10.1109/icassp49357.2023.10096724"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5076586054","display_name":"Kai Li","orcid":"https://orcid.org/0000-0001-6429-8465"},"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"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Li","raw_affiliation_strings":["Tsinghua University,BNRist,Department of Computer Science and Technology,China","Department of Computer Science and Technology, BNRist, Tsinghua University, China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,BNRist,Department of Computer Science and Technology,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048439332","display_name":"Yi Luo","orcid":"https://orcid.org/0000-0002-7447-3885"},"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":"Yi Luo","raw_affiliation_strings":["Tencent AI Lab,Shenzhen,China","Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076586054"],"corresponding_institution_ids":["https://openalex.org/I2250653659","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.9712,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86820938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9993000030517578,"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":0.9988999962806702,"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":0.8637465238571167},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8135278224945068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5339789390563965},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.519154965877533},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5058348178863525},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4667744040489197},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.46254417300224304},{"id":"https://openalex.org/keywords/online-model","display_name":"Online model","score":0.4416294991970062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4347291588783264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.336017370223999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8637465238571167},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8135278224945068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5339789390563965},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.519154965877533},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5058348178863525},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4667744040489197},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.46254417300224304},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.4416294991970062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4347291588783264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.336017370223999},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096724","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1821462560","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2296073425","https://openalex.org/W2460742184","https://openalex.org/W2802023636","https://openalex.org/W2889442120","https://openalex.org/W2898268964","https://openalex.org/W2905741102","https://openalex.org/W2910254446","https://openalex.org/W2938917877","https://openalex.org/W2939518062","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935523","https://openalex.org/W2962935966","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W3015199127","https://openalex.org/W3015654783","https://openalex.org/W3035268204","https://openalex.org/W3041647828","https://openalex.org/W3096518646","https://openalex.org/W3099330747","https://openalex.org/W3104196160","https://openalex.org/W3125815078","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3193846000","https://openalex.org/W3197103473","https://openalex.org/W3204647170","https://openalex.org/W3214142715","https://openalex.org/W4226339160","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6739901393","https://openalex.org/W6757036269","https://openalex.org/W6774995033","https://openalex.org/W6790121257","https://openalex.org/W6803594737"],"related_works":["https://openalex.org/W4225394202","https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W3034302643","https://openalex.org/W1847088711","https://openalex.org/W3036642985","https://openalex.org/W2964335273","https://openalex.org/W1889624880","https://openalex.org/W2369669030"],"abstract_inverted_index":{"While":[0],"the":[1,14,30,57,64,86,110,130,138,151],"performance":[2,27,58,152],"of":[3,17,99],"offline":[4,43,82,93,117,157],"neural":[5,19,44],"speech":[6,45],"separation":[7,46,158],"systems":[8,31,47],"has":[9],"been":[10],"greatly":[11],"advanced":[12],"by":[13],"recent":[15],"development":[16],"novel":[18],"network":[20],"architectures,":[21],"there":[22],"is":[23],"typically":[24],"an":[25,77,81],"inevitable":[26],"gap":[28,153],"between":[29,154],"and":[32,66,80,92,142,145,160],"their":[33,52,161],"online":[34,53,78,91,111,131,162],"variants.":[35,163],"In":[36],"this":[37],"paper,":[38],"we":[39],"investigate":[40],"how":[41],"RNN-based":[42,156],"can":[48,148],"be":[49],"changed":[50],"into":[51],"counterparts":[54],"while":[55],"mitigating":[56],"degradation.":[59],"We":[60,102],"decompose":[61],"or":[62,119],"reorganize":[63],"forward":[65],"backward":[67],"RNN":[68,73],"layers":[69],"in":[70],"a":[71,96,115,120],"bidirectional":[72],"layer":[74,140],"to":[75,88,129],"form":[76],"path":[79],"path,":[83],"which":[84],"enables":[85],"model":[87,100,112,118],"perform":[89],"both":[90],"processing":[94],"with":[95],"same":[97],"set":[98],"parameters.":[101],"further":[103],"introduce":[104],"two":[105,155],"training":[106,122,146],"strategies":[107,147],"for":[108],"improving":[109],"via":[113],"either":[114],"pretrained":[116],"multitask":[121],"objective.":[123],"Experiment":[124],"results":[125],"show":[126],"that":[127,133],"compared":[128],"models":[132,159],"are":[134],"trained":[135],"from":[136],"scratch,":[137],"proposed":[139],"de-composition":[141],"reorganization":[143],"schemes":[144],"effectively":[149],"mitigate":[150]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}