{"id":"https://openalex.org/W4386763644","doi":"https://doi.org/10.1109/waspaa58266.2023.10248134","title":"Flexible Multichannel Speech Enhancement for Noise-Robust Frontend","display_name":"Flexible Multichannel Speech Enhancement for Noise-Robust Frontend","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763644","doi":"https://doi.org/10.1109/waspaa58266.2023.10248134"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5063860258","display_name":"Ante Juki\u0107","orcid":"https://orcid.org/0000-0003-2202-2203"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ante Juki\u0107","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7699807286262512},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483325004577637},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7381136417388916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6469473838806152},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.6295822262763977},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5596567392349243},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5137048959732056},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49338069558143616},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42925623059272766},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4286516606807709},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41236424446105957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31006771326065063},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1820525825023651},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.17173677682876587},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09955772757530212},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08857232332229614}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7699807286262512},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483325004577637},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7381136417388916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6469473838806152},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.6295822262763977},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5596567392349243},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5137048959732056},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49338069558143616},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42925623059272766},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4286516606807709},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41236424446105957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31006771326065063},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1820525825023651},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.17173677682876587},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09955772757530212},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08857232332229614},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa58266.2023.10248134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1973669708","https://openalex.org/W2042860487","https://openalex.org/W2061074721","https://openalex.org/W2077090930","https://openalex.org/W2089586791","https://openalex.org/W2127851351","https://openalex.org/W2131968171","https://openalex.org/W2141998673","https://openalex.org/W2168729028","https://openalex.org/W2242818861","https://openalex.org/W2289480995","https://openalex.org/W2400339399","https://openalex.org/W2517616541","https://openalex.org/W2559809918","https://openalex.org/W2563666542","https://openalex.org/W2752782242","https://openalex.org/W2763188033","https://openalex.org/W2803322398","https://openalex.org/W2889503488","https://openalex.org/W2900212944","https://openalex.org/W3015372568","https://openalex.org/W3015834770","https://openalex.org/W3086154751","https://openalex.org/W3094893851","https://openalex.org/W3097777922","https://openalex.org/W3163217847","https://openalex.org/W3177067699","https://openalex.org/W3196660995","https://openalex.org/W3207360934","https://openalex.org/W3207728800","https://openalex.org/W4225905067","https://openalex.org/W4297841603","https://openalex.org/W4312356750","https://openalex.org/W4316660723","https://openalex.org/W4367597591","https://openalex.org/W4385245566","https://openalex.org/W6690026940","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2396048001","https://openalex.org/W4240587264","https://openalex.org/W2348931051","https://openalex.org/W2109356272","https://openalex.org/W2132495960"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,28,41,97],"flexible":[4,29,79],"multichannel":[5,42],"speech":[6,18],"enhancement":[7],"system":[8,26,80],"with":[9,44,106],"the":[10,58,75,78,90],"main":[11],"goal":[12],"of":[13,16,77,92],"improving":[14],"robustness":[15],"automatic":[17,45],"recognition":[19],"(ASR)":[20],"in":[21,57],"noisy":[22],"conditions.":[23],"The":[24,71],"proposed":[25,52],"combines":[27],"neural":[30],"mask":[31,59],"estimator":[32],"applicable":[33],"to":[34,53,64],"different":[35],"channel":[36],"counts":[37],"and":[38,40,84],"configurations":[39,105],"filter":[43],"reference":[46],"selection.":[47],"A":[48],"transform-attend-concatenate":[49],"layer":[50],"is":[51,62,102],"handle":[54],"cross-channel":[55],"information":[56],"estimator,":[60],"which":[61],"shown":[63],"be":[65],"effective":[66],"for":[67,81,104],"arbitrary":[68],"microphone":[69],"configurations.":[70],"presented":[72],"evaluation":[73],"demonstrates":[74],"effectiveness":[76],"several":[82],"seen":[83],"unseen":[85],"compact":[86],"array":[87],"geometries,":[88],"matching":[89],"performance":[91,101],"fixed":[93],"configuration-specific":[94],"systems.":[95],"Furthermore,":[96],"significantly":[98],"improved":[99],"ASR":[100],"observed":[103],"randomly-placed":[107],"microphones.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}