{"id":"https://openalex.org/W4391021770","doi":"https://doi.org/10.1109/asru57964.2023.10389633","title":"Vsanet: Real-Time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention","display_name":"Vsanet: Real-Time Speech Enhancement Based on Voice Activity Detection and Causal Spatial Attention","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021770","doi":"https://doi.org/10.1109/asru57964.2023.10389633"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5004726078","display_name":"Yuewei Zhang","orcid":"https://orcid.org/0000-0002-9124-0194"},"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":"Yuewei Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031888988","display_name":"Huanbin Zou","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":"Huanbin Zou","raw_affiliation_strings":["Tencent Video Cloud,Shanghai,China","Tencent Video Cloud, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Video Cloud,Shanghai,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Video Cloud, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067937423","display_name":"Jie Zhu","orcid":"https://orcid.org/0000-0002-4941-455X"},"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":"Jie Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Electronic Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.725,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72586692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9951000213623047,"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":0.9951000213623047,"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":0.953499972820282,"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":0.738380491733551},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.7377820014953613},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6343019604682922},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4964912533760071},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3912826180458069},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2983497977256775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.738380491733551},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.7377820014953613},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6343019604682922},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4964912533760071},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3912826180458069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2983497977256775},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W3135230428","https://openalex.org/W4231424160","https://openalex.org/W2120771489","https://openalex.org/W2904739811","https://openalex.org/W2051376034","https://openalex.org/W2275432853","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"The":[0,135],"deep":[1,24],"learning-based":[2],"speech":[3],"enhancement":[4],"(SE)":[5],"methods":[6],"always":[7],"take":[8],"the":[9,18,23,30,34,38,58,86,90,96,100,114,120,139,145],"clean":[10],"speech\u2019s":[11],"waveform":[12],"or":[13],"time-frequency":[14],"spectrum":[15],"feature":[16],"as":[17],"learning":[19,45,60,124,143],"target,":[20],"and":[21,37,75,89,126,144],"train":[22],"neural":[25],"network":[26,92,131],"(DNN)":[27],"by":[28,95],"reducing":[29],"error":[31],"loss":[32,98],"between":[33],"DNN\u2019s":[35],"output":[36],"target.":[39],"This":[40],"is":[41,93,132],"a":[42,69,72,76,106],"conventional":[43],"single-task":[44],"paradigm,":[46],"which":[47,84,148],"has":[48],"been":[49],"proven":[50],"to":[51,112],"be":[52],"effective,":[53],"but":[54],"we":[55,67,104],"find":[56],"that":[57],"multi-task":[59,123,142],"framework":[61,70,125],"can":[62],"improve":[63],"SE":[64,73,130,153],"performance.":[65,154],"Specifically,":[66],"design":[68,105],"containing":[71],"module":[74],"voice":[77],"activity":[78],"detection":[79],"(VAD)":[80],"module,":[81],"both":[82],"of":[83,99,117,141],"share":[85],"same":[87],"encoder,":[88],"whole":[91],"optimized":[94],"weighted":[97],"two":[101],"modules.":[102],"Moreover,":[103],"causal":[107],"spatial":[108],"attention":[109],"(CSA)":[110],"block":[111],"promote":[113],"representation":[115],"capability":[116],"DNN.":[118],"Combining":[119],"VAD":[121],"aided":[122],"CSA":[127,146],"block,":[128,147],"our":[129],"named":[133],"VSANet.":[134],"experimental":[136],"results":[137],"prove":[138],"benefits":[140],"give":[149],"VSANet":[150],"an":[151],"excellent":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}