{"id":"https://openalex.org/W3209490467","doi":"https://doi.org/10.1109/waspaa52581.2021.9632720","title":"Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions","display_name":"Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3209490467","doi":"https://doi.org/10.1109/waspaa52581.2021.9632720","mag":"3209490467"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5071937621","display_name":"Wangyou Zhang","orcid":"https://orcid.org/0000-0003-4500-3515"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wangyou Zhang","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112122495","display_name":"Jing Shi","orcid":"https://orcid.org/0000-0003-3225-7145"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Shi","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090224430","display_name":"Chenda Li","orcid":"https://orcid.org/0000-0003-0299-9914"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenda Li","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, X-LANCE Lab, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071937621"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.8518,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86321354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"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":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/speech-enhancement","display_name":"Speech enhancement","score":0.8034340143203735},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7854864597320557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6563840508460999},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5896381139755249},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.5386422276496887},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.48756760358810425},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.4870296120643616},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4787292182445526},{"id":"https://openalex.org/keywords/performance-enhancement","display_name":"Performance enhancement","score":0.43915510177612305},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43008846044540405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40089091658592224},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08681243658065796},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06844127178192139}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8034340143203735},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7854864597320557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6563840508460999},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5896381139755249},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.5386422276496887},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.48756760358810425},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.4870296120643616},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4787292182445526},{"id":"https://openalex.org/C2986800882","wikidata":"https://www.wikidata.org/wiki/Q7168187","display_name":"Performance enhancement","level":2,"score":0.43915510177612305},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43008846044540405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40089091658592224},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08681243658065796},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06844127178192139},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632720","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W2060108923","https://openalex.org/W2141998673","https://openalex.org/W2148613904","https://openalex.org/W2398042854","https://openalex.org/W2517616541","https://openalex.org/W2526425061","https://openalex.org/W2559260703","https://openalex.org/W2902894493","https://openalex.org/W2909607850","https://openalex.org/W2936774411","https://openalex.org/W2940526039","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2962935966","https://openalex.org/W2972460025","https://openalex.org/W2972541922","https://openalex.org/W2972802573","https://openalex.org/W2995166068","https://openalex.org/W3004309045","https://openalex.org/W3015312544","https://openalex.org/W3015661721","https://openalex.org/W3015788098","https://openalex.org/W3016257794","https://openalex.org/W3027008958","https://openalex.org/W3099330747","https://openalex.org/W3151596526","https://openalex.org/W3151851237","https://openalex.org/W3161766157","https://openalex.org/W3162315798","https://openalex.org/W4288366110","https://openalex.org/W6768303171"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2124672476","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W3168109306","https://openalex.org/W2089240210","https://openalex.org/W4375869276","https://openalex.org/W2131486661","https://openalex.org/W111365173"],"abstract_inverted_index":{"The":[0],"deep":[1],"learning":[2],"based":[3,62],"time-domain":[4,24],"models,":[5],"e.g.":[6],"Conv-TasNet,":[7],"have":[8],"shown":[9],"great":[10],"potential":[11],"in":[12,30,83,152],"both":[13,66],"single-channel":[14],"and":[15,33,68,110,117,142],"multi-channel":[16,60,101],"speech":[17,25,63,115,118,136,149],"enhancement.":[18],"However,":[19],"many":[20],"experiments":[21,73,122],"on":[22,123],"the":[23,40,80,86,98,104,111,124,135,147,153],"enhancement":[26,64,116,150],"model":[27,106],"are":[28,91],"done":[29],"simulated":[31],"conditions,":[32],"it":[34],"is":[35],"not":[36],"well":[37],"studied":[38],"whether":[39],"good":[41],"performance":[42,77,138],"can":[43,132],"generalize":[44],"to":[45,53,65,93],"real-world":[46],"scenarios.":[47],"In":[48],"this":[49,95],"paper,":[50],"we":[51],"aim":[52],"provide":[54],"an":[55],"insightful":[56],"investigation":[57],"of":[58,85,100,114],"applying":[59],"Conv-TasNet":[61,102],"simulation":[67,141],"real":[69,143],"data.":[70],"Our":[71,121],"preliminary":[72],"show":[74,127],"a":[75],"large":[76],"gap":[78],"between":[79,140],"two":[81],"conditions":[82],"terms":[84],"ASR":[87],"performance.":[88],"Several":[89],"approaches":[90,131],"applied":[92],"close":[94],"gap,":[96],"including":[97],"integration":[99],"into":[103],"beamforming":[105],"with":[107],"various":[108],"strategies,":[109],"joint":[112],"training":[113],"recognition":[119,137],"models.":[120],"CHiME-4":[125],"corpus":[126],"that":[128],"our":[129],"proposed":[130],"greatly":[133],"reduce":[134],"discrepancy":[139],"data,":[144],"while":[145],"preserving":[146],"strong":[148],"capability":[151],"frontend.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}