{"id":"https://openalex.org/W4283021642","doi":"https://doi.org/10.21437/interspeech.2022-174","title":"On the Use of Deep Mask Estimation Module for Neural Source Separation Systems","display_name":"On the Use of Deep Mask Estimation Module for Neural Source Separation Systems","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283021642","doi":"https://doi.org/10.21437/interspeech.2022-174"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-174","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-174","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5100399910","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-5668-1402"},"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":"Kai Li","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089952788","display_name":"Xiaolin Hu","orcid":"https://orcid.org/0000-0003-0055-7290"},"institutions":[{"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":"Xiaolin Hu","raw_affiliation_strings":["Department of Computer Science and Technology, BNRist, Tsinghua University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, BNRist, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5089952788"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.0944,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79061713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5328","last_page":"5332"},"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":0.9962000250816345,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6425163745880127},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.544026255607605},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4830949306488037},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47695744037628174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4415613114833832},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13320747017860413}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6425163745880127},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.544026255607605},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4830949306488037},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47695744037628174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4415613114833832},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13320747017860413}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-174","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-174","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W190004713","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W2031647436","https://openalex.org/W2069681747","https://openalex.org/W2117042571","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2291877678","https://openalex.org/W2460742184","https://openalex.org/W2567070169","https://openalex.org/W2952218014","https://openalex.org/W2963443859","https://openalex.org/W2964058413","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3036069164","https://openalex.org/W3096408984","https://openalex.org/W3158652463","https://openalex.org/W3160241658","https://openalex.org/W3160903688","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3214142715"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2077498359"],"abstract_inverted_index":{"Most":[0],"of":[1,16,28,33,60,83,113],"the":[2,29,58,81,104,114,119],"recent":[3,54],"neural":[4],"source":[5,97],"separation":[6,98],"systems":[7],"rely":[8],"on":[9],"a":[10,14,25,44,61,72,93],"masking-based":[11],"pipeline":[12],"where":[13],"set":[15],"multiplicative":[17],"masks":[18],"are":[19],"estimated":[20],"from":[21],"and":[22,66,100],"applied":[23],"to":[24,71,92],"signal":[26],"representation":[27],"input":[30],"mixture.The":[31],"estimation":[32,64,75,87,107,123],"such":[34,84],"masks,":[35],"in":[36],"almost":[37],"all":[38],"network":[39],"architectures,":[40],"is":[41,109],"done":[42],"by":[43,48,89],"single":[45],"layer":[46],"followed":[47],"an":[49,110],"optional":[50],"nonlinear":[51],"activation":[52],"function.However,":[53],"literatures":[55],"have":[56],"investigated":[57],"use":[59],"deep":[62,105],"mask":[63,74,86,106,122],"module":[65,88,108],"observed":[67],"performance":[68],"improvement":[69],"compared":[70],"shallow":[73,121],"module.In":[76],"this":[77],"paper,":[78],"we":[79],"analyze":[80],"role":[82],"deeper":[85],"connecting":[90],"it":[91],"recently":[94],"proposed":[95],"unsupervised":[96],"method,":[99],"empirically":[101],"show":[102],"that":[103],"efficient":[111],"approximation":[112],"so-called":[115],"overseparation-grouping":[116],"paradigm":[117],"with":[118],"conventional":[120],"layers.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}