{"id":"https://openalex.org/W2594647430","doi":"https://doi.org/10.1109/icassp.2017.7952119","title":"DNN-based speech mask estimation for eigenvector beamforming","display_name":"DNN-based speech mask estimation for eigenvector beamforming","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2594647430","doi":"https://doi.org/10.1109/icassp.2017.7952119","mag":"2594647430"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5032296366","display_name":"Lukas Pfeifenberger","orcid":"https://orcid.org/0000-0001-9688-1372"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Lukas Pfeifenberger","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028921456","display_name":"Matthias Z\u00f6hrer","orcid":"https://orcid.org/0000-0002-7406-7924"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Matthias Zohrer","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015798259","display_name":"Franz Pernkopf","orcid":"https://orcid.org/0000-0002-6356-3367"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Franz Pernkopf","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032296366"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":5.1779,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.96391361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"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":0.9988999962806702,"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":0.9975000023841858,"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":0.6975942254066467},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6869632005691528},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6510875225067139},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.6436498165130615},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6007500290870667},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5820639729499817},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.49329012632369995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47118476033210754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.447762131690979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44494277238845825},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4185771346092224},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4119339883327484},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.25303423404693604},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1147250235080719}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6975942254066467},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869632005691528},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6510875225067139},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.6436498165130615},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6007500290870667},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5820639729499817},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.49329012632369995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47118476033210754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447762131690979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44494277238845825},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4185771346092224},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4119339883327484},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25303423404693604},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1147250235080719},{"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.2017.7952119","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W112201544","https://openalex.org/W1492221128","https://openalex.org/W1522301498","https://openalex.org/W1635564296","https://openalex.org/W1988851394","https://openalex.org/W1999542175","https://openalex.org/W2016100027","https://openalex.org/W2032676419","https://openalex.org/W2046869671","https://openalex.org/W2061074721","https://openalex.org/W2099984896","https://openalex.org/W2105921478","https://openalex.org/W2110798204","https://openalex.org/W2113349214","https://openalex.org/W2138939691","https://openalex.org/W2147665979","https://openalex.org/W2158143227","https://openalex.org/W2168013545","https://openalex.org/W2289394825","https://openalex.org/W2291687365","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2401665178","https://openalex.org/W2405316468","https://openalex.org/W2964121744","https://openalex.org/W4210849719","https://openalex.org/W4214498238","https://openalex.org/W4295679937","https://openalex.org/W6631190155","https://openalex.org/W6680324615"],"related_works":["https://openalex.org/W2769441402","https://openalex.org/W2594436708","https://openalex.org/W4360994128","https://openalex.org/W3086240734","https://openalex.org/W2951850672","https://openalex.org/W2789476480","https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W2028846388","https://openalex.org/W4295210860"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,33,61],"present":[4],"an":[5,13],"optimal":[6],"multi-channel":[7],"Wiener":[8],"filter,":[9],"which":[10,32],"consists":[11],"of":[12,41,80,83,88,108,112,127],"eigenvector":[14],"beamformer":[15],"and":[16,45,58,101,131],"a":[17,28,36,42,46],"single-channel":[18],"postfilter.":[19],"We":[20,93,116],"show":[21,117],"that":[22,118],"both":[23,124],"components":[24],"solely":[25],"depend":[26],"on":[27],"speech":[29,91,129],"presence":[30],"probability,":[31],"learn":[34],"using":[35],"deep":[37,43],"neural":[38],"network,":[39],"consisting":[40],"autoencoder":[44],"softmax":[47],"regression":[48],"layer.":[49],"To":[50],"prevent":[51],"the":[52,65,73,77,84,89,98,106,109,113],"DNN":[53],"from":[54],"learning":[55],"specific":[56],"speaker":[57],"noise":[59],"types,":[60],"do":[62],"not":[63],"use":[64],"signal":[66],"energy":[67],"as":[68,105],"input":[69],"feature,":[70],"but":[71],"rather":[72],"cosine":[74],"distance":[75],"between":[76],"dominant":[78],"eigenvectors":[79],"consecutive":[81],"frames":[82],"power":[85],"spectral":[86],"density":[87],"noisy":[90],"signal.":[92],"compare":[94],"our":[95,119],"system":[96,111,120],"against":[97],"BeamformIt":[99],"toolkit,":[100],"state-of-the-art":[102],"approaches":[103],"such":[104],"front-end":[107],"best":[110],"CHiME3":[114],"challenge.":[115],"yields":[121],"superior":[122],"results,":[123],"in":[125],"terms":[126],"perceptual":[128],"quality":[130],"classification":[132],"error.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}