{"id":"https://openalex.org/W4403127014","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694149","title":"Learning-Based Multi-Channel Speech Presence Probability Estimation using A Low-Parameter Model and Integration with MVDR Beamforming for Multi-Channel Speech Enhancement","display_name":"Learning-Based Multi-Channel Speech Presence Probability Estimation using A Low-Parameter Model and Integration with MVDR Beamforming for Multi-Channel Speech Enhancement","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403127014","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694149"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5007499353","display_name":"Shuai Tao","orcid":"https://orcid.org/0000-0003-2223-0205"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Shuai Tao","raw_affiliation_strings":["Audio Analysis Lab, Electronic Systems, Aalborg University,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, Electronic Systems, Aalborg University,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088787456","display_name":"Pejman Mowlaee","orcid":"https://orcid.org/0000-0003-0136-8002"},"institutions":[{"id":"https://openalex.org/I4210155671","display_name":"GN Store Nord (Denmark)","ror":"https://ror.org/04ck29617","country_code":"DK","type":"company","lineage":["https://openalex.org/I4210155671"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Pejman Mowlaee","raw_affiliation_strings":["GN Audio A/S,Ballerup,Denmark,2750"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GN Audio A/S,Ballerup,Denmark,2750","institution_ids":["https://openalex.org/I4210155671"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041263382","display_name":"Jesper Rindom Jensen","orcid":"https://orcid.org/0000-0001-6023-8270"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Jesper Rindom Jensen","raw_affiliation_strings":["Audio Analysis Lab, Electronic Systems, Aalborg University,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, Electronic Systems, Aalborg University,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Audio Analysis Lab, Electronic Systems, Aalborg University,Aalborg,Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab, Electronic Systems, Aalborg University,Aalborg,Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7515,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91552282,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"104"},"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":0.9977999925613403,"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/T11309","display_name":"Music and Audio Processing","score":0.996399998664856,"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/beamforming","display_name":"Beamforming","score":0.7796221375465393},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.7377460598945618},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6885305643081665},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6342689990997314},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5945116877555847},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.4304795563220978},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3646087646484375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2695367932319641},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.23006001114845276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.216803640127182},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.07144990563392639}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7796221375465393},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.7377460598945618},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6885305643081665},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6342689990997314},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5945116877555847},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.4304795563220978},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3646087646484375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2695367932319641},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.23006001114845276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.216803640127182},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.07144990563392639}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/155b5bc7-dd51-47e0-abb6-5d541721ec0e","is_oa":false,"landing_page_url":"https://ieeexplore.ieee.org/document/10694149/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tao, S, Mowlaee, P, Jensen, J R & Christensen, M G 2024, Learning-Based Multi-Channel Speech Presence Probability Estimation using A Low-Parameter Model and Integration with MVDR Beamforming for Multi-Channel Speech Enhancement. in 2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)., 10694149, IEEE (Institute of Electrical and Electronics Engineers), International Workshop on Acoustic Signal Enhancement (IWAENC), pp. 100-104, 18th International Workshop on Acoustic Signal Enhancement, IWAENC 2024, Aalborg, Denmark, 09/09/2024. https://doi.org/10.1109/IWAENC61483.2024.10694149","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2012770786","https://openalex.org/W2033178790","https://openalex.org/W2033875152","https://openalex.org/W2040909219","https://openalex.org/W2051428568","https://openalex.org/W2067295501","https://openalex.org/W2089586791","https://openalex.org/W2118354544","https://openalex.org/W2120608389","https://openalex.org/W2127292597","https://openalex.org/W2146324387","https://openalex.org/W2147299274","https://openalex.org/W2148613904","https://openalex.org/W2168729028","https://openalex.org/W2398042854","https://openalex.org/W2593116425","https://openalex.org/W2804084629","https://openalex.org/W2945191446","https://openalex.org/W3015791598","https://openalex.org/W3102244871","https://openalex.org/W3147539069","https://openalex.org/W3161480375","https://openalex.org/W3163591408","https://openalex.org/W4225905067","https://openalex.org/W4232282348","https://openalex.org/W4321608474","https://openalex.org/W4385823063","https://openalex.org/W6631190155","https://openalex.org/W6782481672"],"related_works":["https://openalex.org/W2963170046","https://openalex.org/W2376244802","https://openalex.org/W1971477554","https://openalex.org/W2158075901","https://openalex.org/W818226659","https://openalex.org/W2923631784","https://openalex.org/W2130785056","https://openalex.org/W2567141277","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Learning-based":[0],"a":[1,123,149,181],"posteriori":[2],"speech":[3,40,78,87,120,151,172,200],"presence":[4],"probability":[5],"(SPP)":[6],"estimation":[7,193],"has":[8],"shown":[9],"high":[10],"accuracy":[11],"in":[12,153],"non-stationary":[13],"noise":[14,72,114,156],"environments.":[15],"In":[16],"this":[17],"work,":[18],"we":[19,146],"propose":[20],"using":[21,95],"multi-channel":[22,26,39,119,199],"information":[23],"to":[24,37,62,170],"estimate":[25,63,131],"SPP":[27],"(MC-SPP)":[28],"based":[29],"on":[30,67],"deep":[31],"neural":[32],"networks":[33],"(DNNs),":[34],"which":[35],"contribute":[36],"improving":[38],"enhancement":[41,121,201],"performance.":[42,202],"Firstly,":[43],"with":[44,110,180],"the":[45,49,52,64,68,71,85,90,96,101,111,129,141,154],"observed":[46],"signal":[47],"and":[48,76,113,160,165],"MC-SPP":[50,69,130],"as":[51],"training":[53,159],"data":[54],"pairs,":[55],"one":[56],"low-parameter":[57],"DNN":[58],"model":[59],"is":[60,93,108,132,137],"trained":[61],"MC-SPP.":[65],"Based":[66],"estimate,":[70],"power":[73],"density":[74],"(PSD)":[75],"clean":[77,86,112],"PSD":[79,88],"matrices":[80],"are":[81,168],"updated":[82],"recursively.":[83],"With":[84],"matrix,":[89],"steering":[91],"vector":[92],"computed":[94,109],"covariance":[97],"subtraction":[98],"method.":[99],"Subsequently,":[100],"minimum":[102],"variance":[103],"distortionless":[104],"response":[105],"(MVDR)":[106],"weight":[107],"matrices.":[115],"To":[116],"further":[117,197],"improve":[118,198],"performance,":[122],"new":[124],"MVDR":[125,142],"modification":[126],"guided":[127],"by":[128,139],"proposed.":[133],"Finally,":[134],"spatial":[135],"filtering":[136],"performed":[138],"integrating":[140],"beamforming.":[143],"For":[144],"experiments,":[145],"spatially":[147],"synthesize":[148],"real":[150],"dataset":[152],"isotropic":[155],"fields":[157],"for":[158],"testing.":[161],"The":[162,174],"PESQ,":[163],"STOI,":[164],"DNSMOS":[166],"scores":[167],"used":[169],"evaluate":[171],"quality.":[173],"experimental":[175],"results":[176],"show":[177],"that,":[178],"compared":[179],"recently":[182],"proposed":[183,187],"DNN-guided":[184],"approach,":[185],"our":[186],"method":[188],"provides":[189],"an":[190],"effective":[191],"statistics":[192],"approach":[194],"that":[195],"can":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}