{"id":"https://openalex.org/W3144062511","doi":"https://doi.org/10.1109/slt48900.2021.9383528","title":"WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation","display_name":"WPD++: An Improved Neural Beamformer for Simultaneous Speech Separation and Dereverberation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3144062511","doi":"https://doi.org/10.1109/slt48900.2021.9383528","mag":"3144062511"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5031088292","display_name":"Zhaoheng Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhaoheng Ni","raw_affiliation_strings":["City University of New York, New York, NY, USA","Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"City University of New York, New York, NY, USA","institution_ids":["https://openalex.org/I174216632"]},{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407019","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0002-0031-9156"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100672630","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0002-3126-5103"},"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":"Bo Wu","raw_affiliation_strings":["Tencent AI lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shixiong Zhang","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, WA, USA"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, WA, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I Mandel","raw_affiliation_strings":["City University of New York, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"City University of New York, New York, NY, USA","institution_ids":["https://openalex.org/I174216632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031088292"],"corresponding_institution_ids":["https://openalex.org/I174216632","https://openalex.org/I4210108985"],"apc_list":null,"apc_paid":null,"fwci":1.0665,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75936444,"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":"817","last_page":"824"},"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":0.9984999895095825,"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":0.9976000189781189,"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":0.6662813425064087},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641054153442383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6453515291213989},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5772643089294434},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.5511809587478638},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5205529928207397},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4946875274181366},{"id":"https://openalex.org/keywords/minimum-mean-square-error","display_name":"Minimum mean square error","score":0.46305394172668457},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.41228726506233215},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.32200461626052856},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25635576248168945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21327075362205505},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1542212963104248},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10357892513275146}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6662813425064087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641054153442383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6453515291213989},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5772643089294434},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.5511809587478638},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5205529928207397},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4946875274181366},{"id":"https://openalex.org/C90652560","wikidata":"https://www.wikidata.org/wiki/Q11091747","display_name":"Minimum mean square error","level":3,"score":0.46305394172668457},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.41228726506233215},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.32200461626052856},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25635576248168945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21327075362205505},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1542212963104248},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10357892513275146},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":0.7200000286102295}],"awards":[],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1891272442","https://openalex.org/W2021525189","https://openalex.org/W2061074721","https://openalex.org/W2140571699","https://openalex.org/W2143169494","https://openalex.org/W2150678643","https://openalex.org/W2242685705","https://openalex.org/W2291877678","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2408713104","https://openalex.org/W2517616541","https://openalex.org/W2561557072","https://openalex.org/W2640112133","https://openalex.org/W2714487941","https://openalex.org/W2747732471","https://openalex.org/W2889540509","https://openalex.org/W2909607850","https://openalex.org/W2939497224","https://openalex.org/W2952218014","https://openalex.org/W2973231102","https://openalex.org/W2989287578","https://openalex.org/W2996969697","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015306655","https://openalex.org/W3015390914","https://openalex.org/W3015661721","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3028504434","https://openalex.org/W3096073522","https://openalex.org/W3097173744","https://openalex.org/W3099177480","https://openalex.org/W3099330747","https://openalex.org/W3185109982","https://openalex.org/W4288366110","https://openalex.org/W6713729801","https://openalex.org/W6761806390","https://openalex.org/W6774687970"],"related_works":["https://openalex.org/W818226659","https://openalex.org/W2996333928","https://openalex.org/W2009075871","https://openalex.org/W2132841313","https://openalex.org/W2518591292","https://openalex.org/W2105408150","https://openalex.org/W1976800395","https://openalex.org/W2548445082","https://openalex.org/W2361247493","https://openalex.org/W2606661315"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"at":[3],"eliminating":[4],"the":[5,14,27,43,49,68,77,87,94,103,118,122,126,136,141,152,160],"interfering":[6],"speakers'":[7],"speech,":[8],"additive":[9],"noise,":[10],"and":[11,40,71,102,121,140,164],"reverberation":[12],"from":[13],"noisy":[15],"multi-talker":[16],"speech":[17,22,120,162],"mixture":[18],"that":[19,151],"benefits":[20],"automatic":[21],"recognition":[23],"(ASR)":[24],"backend.":[25],"While":[26],"recently":[28],"proposed":[29,153],"Weighted":[30],"Power":[31],"minimization":[32],"Distortionless":[33],"response":[34],"(WPD)":[35],"beamformer":[36,59,143],"can":[37],"perform":[38],"separation":[39],"dereverberation":[41],"simultaneously,":[42],"noise":[44],"cancellation":[45],"component":[46],"still":[47],"has":[48],"potential":[50],"to":[51,113,134],"progress.":[52],"We":[53],"propose":[54],"an":[55,63,145],"improved":[56,84],"neural":[57],"WPD":[58,70],"called":[60],"\"WPD++\"":[61],"by":[62,85],"enhanced":[64,119,161],"beamforming":[65,81],"module":[66,82],"in":[67,144],"conventional":[69],"a":[72],"multi-objective":[73,91],"loss":[74],"function":[75],"for":[76],"joint":[78],"training.":[79],"The":[80,148],"is":[83,110,132],"utilizing":[86],"spatio-temporal":[88],"correlation.":[89],"A":[90],"loss,":[92],"including":[93],"complex":[95],"spectra":[96],"domain":[97,105],"scale-invariant":[98],"signal-to-noise":[99],"ratio":[100],"(C-Si-SNR)":[101],"magnitude":[104],"mean":[106],"square":[107],"error":[108,166],"(Mag-MSE),":[109],"properly":[111],"designed":[112],"make":[114],"multiple":[115],"constraints":[116],"on":[117,159],"desired":[123],"power":[124],"of":[125,169],"dry":[127],"clean":[128],"signal.":[129],"Joint":[130],"training":[131],"conducted":[133],"optimize":[135],"complex-valued":[137],"mask":[138],"estimator":[139],"WPD++":[142,154],"end-to-end":[146],"way.":[147],"results":[149],"show":[150],"outperforms":[155],"several":[156],"state-of-the-art":[157],"beamformers":[158],"quality":[163],"word":[165],"rate":[167],"(WER)":[168],"ASR.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}