{"id":"https://openalex.org/W4221165117","doi":"https://doi.org/10.1109/icassp43922.2022.9746055","title":"The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO Convolutional Recurrent Network for Multi Channel Speech Enhancement and Speech Recognition","display_name":"The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO Convolutional Recurrent Network for Multi Channel Speech Enhancement and Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221165117","doi":"https://doi.org/10.1109/icassp43922.2022.9746055"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746055","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 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/A5100642253","display_name":"Jingdong Li","orcid":"https://orcid.org/0000-0003-2335-6280"},"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":true,"raw_author_name":"Jingdong Li","raw_affiliation_strings":["Tencent PCG,AI Interaction Division","AI Interaction Division, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,AI Interaction Division","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Interaction Division, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100989234","display_name":"Yuanyuan Zhu","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":"Yuanyuan Zhu","raw_affiliation_strings":["Tencent PCG,AI Interaction Division","AI Interaction Division, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,AI Interaction Division","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Interaction Division, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101426326","display_name":"Dawei Luo","orcid":"https://orcid.org/0009-0004-4158-0811"},"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":"Dawei Luo","raw_affiliation_strings":["Tencent PCG,AI Interaction Division","AI Interaction Division, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,AI Interaction Division","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Interaction Division, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083093046","display_name":"Yun Liu","orcid":"https://orcid.org/0000-0002-9567-5531"},"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":"Yun Liu","raw_affiliation_strings":["Tencent PCG,AI Interaction Division","AI Interaction Division, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,AI Interaction Division","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Interaction Division, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102067914","display_name":"Guohui Cui","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":"Guohui Cui","raw_affiliation_strings":["Tencent PCG,AI Interaction Division","AI Interaction Division, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,AI Interaction Division","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Interaction Division, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100380854","display_name":"Zhaoxia Li","orcid":"https://orcid.org/0000-0002-8045-6176"},"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":"Zhaoxia Li","raw_affiliation_strings":["Tencent PCG,AI Interaction Division","AI Interaction Division, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,AI Interaction Division","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"AI Interaction Division, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100642253"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":1.7183,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86793049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9211","last_page":"9215"},"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":0.9973999857902527,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.740759551525116},{"id":"https://openalex.org/keywords/mimo","display_name":"MIMO","score":0.6987953186035156},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6761560440063477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6632524728775024},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5899583697319031},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5322088599205017},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4984395503997803},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4366300106048584},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.42626306414604187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26970863342285156},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.21614399552345276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14040184020996094},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1008552610874176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.740759551525116},{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.6987953186035156},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6761560440063477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6632524728775024},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5899583697319031},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5322088599205017},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4984395503997803},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4366300106048584},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.42626306414604187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26970863342285156},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.21614399552345276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14040184020996094},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1008552610874176},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746055","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746055","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2060108923","https://openalex.org/W2066218102","https://openalex.org/W2078528584","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2517616541","https://openalex.org/W2962866211","https://openalex.org/W2991361823","https://openalex.org/W3015679215","https://openalex.org/W3032514799","https://openalex.org/W3036601975","https://openalex.org/W3120336970","https://openalex.org/W3162341667","https://openalex.org/W3198156015","https://openalex.org/W3213747130","https://openalex.org/W4205689591","https://openalex.org/W4225270933","https://openalex.org/W6780218876","https://openalex.org/W6783462664","https://openalex.org/W6803839537"],"related_works":["https://openalex.org/W4375869276","https://openalex.org/W4221152531","https://openalex.org/W2653453860","https://openalex.org/W2046186789","https://openalex.org/W2314295168","https://openalex.org/W2355125052","https://openalex.org/W37007395","https://openalex.org/W2744059046","https://openalex.org/W2810291168","https://openalex.org/W2396333194"],"abstract_inverted_index":{"This":[0],"paper":[1],"described":[2],"the":[3,32,51,58,73,95,106],"PCG-AIID":[4],"system":[5,84],"for":[6],"L3DAS22":[7,90],"challenge":[8,91],"in":[9,15,88],"Task":[10],"1:":[11],"3D":[12],"speech":[13,27,74],"enhancement":[14],"office":[16],"reverberant":[17],"environment.":[18],"We":[19],"proposed":[20],"a":[21,35,61,81],"two-stage":[22],"framework":[23],"to":[24,45,71],"address":[25],"multi-channel":[26,55],"denoising":[28],"and":[29,38,64,78,92,102],"dereverberation.":[30],"In":[31,57],"first":[33],"stage,":[34,60],"multiple":[36,39,62],"input":[37,63],"out-put":[40,66],"(MIMO)":[41],"network":[42,68],"is":[43,69],"applied":[44,70],"remove":[46],"background":[47],"noise":[48],"while":[49,98],"maintaining":[50],"spatial":[52],"characteristics":[53],"of":[54],"signals.":[56],"second":[59],"single":[65],"(MISO)":[67],"enhance":[72],"from":[75],"desired":[76],"direction":[77],"post-filtering.":[79],"As":[80],"result,":[82],"our":[83],"ranked":[85],"3rd":[86],"place":[87],"ICASSP2022":[89],"significantly":[93],"outperforms":[94],"baseline":[96],"system,":[97],"achieving":[99],"3.2%":[100],"WER":[101],"0.972":[103],"STOI":[104],"on":[105],"blind":[107],"test-set.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
