{"id":"https://openalex.org/W2398042854","doi":"https://doi.org/10.1109/icassp.2016.7471664","title":"Neural network based spectral mask estimation for acoustic beamforming","display_name":"Neural network based spectral mask estimation for acoustic beamforming","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398042854","doi":"https://doi.org/10.1109/icassp.2016.7471664","mag":"2398042854"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5006131416","display_name":"Jahn Heymann","orcid":null},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jahn Heymann","raw_affiliation_strings":["Department of Communications Engineering, University of Paderborn, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of Paderborn, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011191228","display_name":"Lukas Drude","orcid":"https://orcid.org/0000-0003-3683-5432"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lukas Drude","raw_affiliation_strings":["Department of Communications Engineering, University of Paderborn, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of Paderborn, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082075598","display_name":"Reinhold Haeb\u2010Umbach","orcid":"https://orcid.org/0000-0001-9468-7330"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Reinhold Haeb-Umbach","raw_affiliation_strings":["Department of Communications Engineering, University of Paderborn, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, University of Paderborn, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":42.6279,"has_fulltext":false,"cited_by_count":499,"citation_normalized_percentile":{"value":0.99923776,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"196","last_page":"200"},"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":0.9987999796867371,"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":0.9987999796867371,"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":0.8236340284347534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7306253910064697},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6766459941864014},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5861298441886902},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5827825665473938},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5621720552444458},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.55696040391922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32143235206604004},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2968994975090027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15291965007781982},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12948071956634521}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8236340284347534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7306253910064697},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6766459941864014},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5861298441886902},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5827825665473938},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5621720552444458},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.55696040391922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32143235206604004},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2968994975090027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15291965007781982},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12948071956634521},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/icassp.2016.7471664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471664","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1542280630","https://openalex.org/W1591801644","https://openalex.org/W1836465849","https://openalex.org/W1931312565","https://openalex.org/W2003203076","https://openalex.org/W2012910847","https://openalex.org/W2031583051","https://openalex.org/W2043216213","https://openalex.org/W2046317813","https://openalex.org/W2095705004","https://openalex.org/W2100335648","https://openalex.org/W2103088716","https://openalex.org/W2148613904","https://openalex.org/W2150355110","https://openalex.org/W2158143227","https://openalex.org/W2171784699","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2402302915","https://openalex.org/W2499512572","https://openalex.org/W2534981247","https://openalex.org/W2949117887","https://openalex.org/W6631943919","https://openalex.org/W6635446068","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6674864272","https://openalex.org/W6712909570"],"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/W2158075901","https://openalex.org/W2567141277","https://openalex.org/W3096184950","https://openalex.org/W2770665941","https://openalex.org/W2782782444"],"abstract_inverted_index":{"We":[0,56,106,122],"present":[1],"a":[2],"neural":[3],"network":[4,11,42,66,91,151],"based":[5],"approach":[6],"to":[7,14,36,63,114,140],"acoustic":[8],"beamforming.":[9],"The":[10,41,145],"is":[12,44,61],"used":[13,35],"estimate":[15],"spectral":[16],"masks":[17],"from":[18],"which":[19,31],"the":[20,38,47,50,54,65,72,148],"Cross-Power":[21],"Spectral":[22],"Density":[23],"matrices":[24],"of":[25,46,53,84,133],"speech":[26,69,79,135,141],"and":[27,49,80,97,117,137],"noise":[28],"are":[29,34,86,152],"estimated,":[30],"in":[32,131],"turn":[33],"compute":[37],"beamformer":[39],"coefficients.":[40],"training":[43],"independent":[45],"number":[48],"geometric":[51],"configuration":[52],"microphones.":[55],"further":[57],"show":[58,123],"that":[59,124],"it":[60],"possible":[62],"train":[64],"on":[67],"clean":[68],"only,":[70],"avoiding":[71],"need":[73],"for":[74,147],"stereo":[75],"data":[76],"with":[77,92,110,138],"separated":[78],"noise.":[81],"Two":[82],"types":[83],"networks":[85],"evaluated.":[87],"One":[88],"small":[89],"feed-forward":[90,150],"only":[93],"one":[94,98],"hidden":[95],"layer":[96],"more":[99],"elaborated":[100],"bi-directional":[101],"Long":[102],"Short-Term":[103],"Memory":[104],"network.":[105],"compare":[107],"our":[108,125],"system":[109,126],"different":[111,119],"parametric":[112],"approaches":[113],"mask":[115],"estimation":[116],"using":[118],"beamforming":[120],"algorithms.":[121],"yields":[127],"superior":[128],"results,":[129],"both":[130],"terms":[132],"perceptual":[134],"quality":[136],"respect":[139],"recognition":[142],"error":[143],"rate.":[144],"results":[146],"simple":[149],"especially":[153],"encouraging":[154],"considering":[155],"its":[156],"low":[157],"computational":[158],"requirements.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":31},{"year":2024,"cited_by_count":38},{"year":2023,"cited_by_count":50},{"year":2022,"cited_by_count":55},{"year":2021,"cited_by_count":76},{"year":2020,"cited_by_count":74},{"year":2019,"cited_by_count":68},{"year":2018,"cited_by_count":54},{"year":2017,"cited_by_count":37},{"year":2016,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}