{"id":"https://openalex.org/W4225320033","doi":"https://doi.org/10.1109/icassp43922.2022.9747237","title":"Audio-Visual Multi-Channel Speech Separation, Dereverberation and Recognition","display_name":"Audio-Visual Multi-Channel Speech Separation, Dereverberation and Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225320033","doi":"https://doi.org/10.1109/icassp43922.2022.9747237"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747237","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":"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/A5042515126","display_name":"Guinan Li","orcid":"https://orcid.org/0000-0002-2206-0237"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guinan Li","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"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","HK"],"is_corresponding":false,"raw_author_name":"Jianwei Yu","raw_affiliation_strings":["The Chinese University of Hong Kong","Tencent AI lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tencent AI lab","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6611,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.85889149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6042","last_page":"6046"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9968000054359436,"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/speech-recognition","display_name":"Speech recognition","score":0.8300826549530029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878148555755615},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6279164552688599},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5311810970306396},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4501150846481323},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41448426246643066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4076518714427948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3302954435348511},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10069116950035095}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8300826549530029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878148555755615},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6279164552688599},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5311810970306396},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4501150846481323},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41448426246643066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4076518714427948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3302954435348511},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10069116950035095},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747237","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1503933356","https://openalex.org/W1971168548","https://openalex.org/W2076462394","https://openalex.org/W2125114513","https://openalex.org/W2140571699","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2159220049","https://openalex.org/W2164502538","https://openalex.org/W2168729028","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2398972335","https://openalex.org/W2589857635","https://openalex.org/W2609317876","https://openalex.org/W2640112133","https://openalex.org/W2747732471","https://openalex.org/W2794289187","https://openalex.org/W2800675406","https://openalex.org/W2803322398","https://openalex.org/W2889503488","https://openalex.org/W2890952074","https://openalex.org/W2899625056","https://openalex.org/W2909607850","https://openalex.org/W2935794029","https://openalex.org/W2939360348","https://openalex.org/W2964171275","https://openalex.org/W2964283370","https://openalex.org/W2972693890","https://openalex.org/W2973231102","https://openalex.org/W3006974783","https://openalex.org/W3008400075","https://openalex.org/W3008762051","https://openalex.org/W3011424113","https://openalex.org/W3015306655","https://openalex.org/W3015383493","https://openalex.org/W3015679215","https://openalex.org/W3097966334","https://openalex.org/W3160348851","https://openalex.org/W4289665794","https://openalex.org/W6754392867","https://openalex.org/W6777451999"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2547793174","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"Despite":[0],"the":[1,18,37,86,93,121,130,139,147,152,163],"rapid":[2],"advance":[3],"of":[4,12,39,78,85,92,185],"automatic":[5],"speech":[6,15,47,57,68,156,167],"recognition":[7,11,60,72,132,160,170],"(ASR)":[8],"technologies,":[9],"accurate":[10],"cocktail":[13],"party":[14],"characterised":[16],"by":[17,36,176],"interference":[19],"from":[20],"overlapping":[21,56],"speakers,":[22],"background":[23],"noise":[24],"and":[25,59,71,111,123,126,141,159,169],"room":[26],"reverberation":[27],"remains":[28],"a":[29,75,177],"highly":[30],"challenging":[31],"task":[32],"to":[33,42],"date.":[34],"Motivated":[35],"invariance":[38],"visual":[40,79,95],"modality":[41,96],"acoustic":[43],"signal":[44],"corruption,":[45],"audio-visual":[46,66,154,165],"enhancement":[48],"techniques":[49],"have":[50],"been":[51],"developed,":[52],"although":[53],"predominantly":[54],"targeting":[55],"separation":[58,122,168],"tasks.":[61],"In":[62],"this":[63],"paper,":[64],"an":[65],"multi-channel":[67,155,166],"separation,":[69,157],"dereverberation":[70,106,124,158,174],"approach":[73],"featuring":[74],"full":[76],"incorporation":[77],"information":[80],"into":[81],"all":[82],"three":[83],"stages":[84],"system":[87,133,161,171],"is":[88,101,134],"proposed.":[89],"The":[90,115],"advantage":[91],"additional":[94],"over":[97],"using":[98,136],"audio":[99],"only":[100],"demonstrated":[102],"on":[103,109,138,146],"two":[104],"neural":[105],"approaches":[107],"based":[108],"DNN-WPE":[110],"spectral":[112],"mapping":[113],"respectively.":[114],"learning":[116],"cost":[117],"function":[118],"mismatch":[119],"between":[120],"models":[125],"their":[127],"integration":[128],"with":[129],"back-end":[131],"minimised":[135],"fine-tuning":[137],"MSE":[140],"LF-MMI":[142],"criteria.":[143],"Experiments":[144],"conducted":[145],"LRS2":[148],"dataset":[149],"suggest":[150],"that":[151],"proposed":[153],"outperforms":[162],"baseline":[164],"containing":[172],"no":[173],"module":[175],"statistically":[178],"significant":[179],"word":[180],"error":[181],"rate":[182],"(WER)":[183],"reduction":[184],"2.06":[186],"%":[187,190],"absolute":[188],"(8.77":[189],"relative).":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}