{"id":"https://openalex.org/W4319586729","doi":"https://doi.org/10.1109/iscslp57327.2022.10037878","title":"Masking-based Neural Beamformer for Multichannel Speech Enhancement","display_name":"Masking-based Neural Beamformer for Multichannel Speech Enhancement","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586729","doi":"https://doi.org/10.1109/iscslp57327.2022.10037878"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037878","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5068044387","display_name":"Shuai Nie","orcid":"https://orcid.org/0000-0002-8078-6829"},"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":true,"raw_author_name":"Shuai Nie","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108575841","display_name":"Shan Liang","orcid":"https://orcid.org/0000-0002-9734-9166"},"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":"Shan Liang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084649692","display_name":"Zhanlei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhanlei Yang","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032487123","display_name":"Longshuai Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Longshuai Xiao","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039635290","display_name":"Wenju Liu","orcid":"https://orcid.org/0000-0001-9088-8282"},"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":"Wenju Liu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"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":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation,Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, National Laboratory of Pattern Recognition, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5068044387"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":0.2455,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45560821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"125","last_page":"129"},"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":0.9987000226974487,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.8208065032958984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7735486626625061},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6711392998695374},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6464686989784241},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.623314619064331},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5882304906845093},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4872838258743286},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4695003032684326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30421486496925354},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16041690111160278},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.10758432745933533},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.06505551934242249}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8208065032958984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735486626625061},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6711392998695374},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6464686989784241},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.623314619064331},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5882304906845093},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4872838258743286},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4695003032684326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30421486496925354},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16041690111160278},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.10758432745933533},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.06505551934242249},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037878","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037878","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1501033557","https://openalex.org/W1542280630","https://openalex.org/W1552314771","https://openalex.org/W1974387177","https://openalex.org/W2068463586","https://openalex.org/W2089586791","https://openalex.org/W2120608389","https://openalex.org/W2141998673","https://openalex.org/W2164502538","https://openalex.org/W2166547995","https://openalex.org/W2168729028","https://openalex.org/W2284628133","https://openalex.org/W2399153348","https://openalex.org/W2407277936","https://openalex.org/W2593116425","https://openalex.org/W2599685671","https://openalex.org/W2640112133","https://openalex.org/W2766719746","https://openalex.org/W2889048668","https://openalex.org/W2900893004","https://openalex.org/W2921496354","https://openalex.org/W2962866211","https://openalex.org/W2963242190","https://openalex.org/W2971417062","https://openalex.org/W2972802573","https://openalex.org/W2982471419","https://openalex.org/W3097173744","https://openalex.org/W6695553435","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W4311414679","https://openalex.org/W2923631784","https://openalex.org/W818226659","https://openalex.org/W3081694532","https://openalex.org/W2158075901","https://openalex.org/W2567141277","https://openalex.org/W3124036039","https://openalex.org/W2130785056"],"abstract_inverted_index":{"Masking":[0,12],"and":[1,37,93,110,118,127,138,178],"beamforming":[2,30,46,111],"techniques":[3],"have":[4],"shown":[5],"considerable":[6],"promise":[7],"for":[8,159],"multichannel":[9],"speech":[10,22,35,176,179],"enhancement.":[11],"technology":[13,31],"can":[14,32],"significantly":[15],"reduce":[16],"noise,":[17],"but":[18],"inevitably":[19],"leads":[20],"to":[21,106,145,153],"distortion,":[23],"especially":[24],"in":[25,41,67,112,136,173],"far-field":[26],"reverb":[27,137],"environments.":[28],"While":[29],"effectively":[33],"avoid":[34],"distortion":[36],"perform":[38],"very":[39],"well":[40],"reverberant":[42],"conditions.":[43],"Obviously,":[44],"masking-based":[45],"scheme":[47],"is":[48,168],"a":[49,100,113,147],"wise":[50],"alternative.":[51],"However,":[52],"most":[53],"methods":[54,172],"use":[55,146],"fixed":[56,151],"or":[57,79],"adaptive":[58],"beamformers":[59,152],"as":[60],"spatial":[61],"filters,":[62],"which":[63],"are":[64,121],"either":[65],"desinged":[66],"advance":[68],"under":[69],"certain":[70],"sound":[71],"field":[72],"assumption,":[73],"with":[74,89,170],"limited":[75],"noise":[76,140],"reduction":[77],"ability,":[78],"involve":[80],"the":[81,125,133,165],"complex":[82],"matrix":[83],"inverse":[84],"operation":[85],"of":[86,149,175],"each":[87],"frequency,":[88],"high":[90],"computational":[91],"complexity":[92],"instability.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98,142],"propose":[99,144],"fully":[101],"learnable":[102],"masking":[103,109],"neural":[104,119],"beamformer":[105,120],"jointly":[107,122],"model":[108],"data-driven":[114],"manner.":[115],"Mask":[116],"prediction":[117],"optimized":[123],"by":[124],"spectrum":[126],"waveform":[128],"approximation":[129],"objectives.":[130],"To":[131],"improve":[132],"directional":[134,155],"discrimination":[135],"diffuse":[139],"environments,":[141],"further":[143],"pair":[148],"complementary":[150],"exploit":[154],"coherence":[156],"feature":[157],"(DCF)":[158],"mask":[160],"prediction.":[161],"Systematic":[162],"experiments":[163],"demonstrate":[164],"proposed":[166],"approach":[167],"competitive":[169],"abailable":[171],"terms":[174],"enhancement":[177],"recognition.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}