{"id":"https://openalex.org/W2803583024","doi":"https://doi.org/10.1109/icassp.2018.8461669","title":"Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition","display_name":"Exploring Practical Aspects of Neural Mask-Based Beamforming for Far-Field Speech Recognition","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2803583024","doi":"https://doi.org/10.1109/icassp.2018.8461669","mag":"2803583024"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5064522438","display_name":"Christoph Boeddeker","orcid":"https://orcid.org/0000-0002-8701-1567"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christoph Boeddeker","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["Microsoft AI and Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft AI and Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, Paderborn University, Paderborn, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communications Engineering, Paderborn University, Paderborn, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6697","last_page":"6701"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991000294685364,"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":0.9976999759674072,"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/computer-science","display_name":"Computer science","score":0.7610176801681519},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.7035237550735474},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6814299821853638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6709427237510681},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6164006590843201},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5580706596374512},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5125067234039307},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4845201373100281},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.47763028740882874},{"id":"https://openalex.org/keywords/adaptive-beamformer","display_name":"Adaptive beamformer","score":0.4531760513782501},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4335954487323761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4150727391242981},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3783377408981323},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07744252681732178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610176801681519},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7035237550735474},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6814299821853638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6709427237510681},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6164006590843201},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5580706596374512},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5125067234039307},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4845201373100281},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.47763028740882874},{"id":"https://openalex.org/C33378366","wikidata":"https://www.wikidata.org/wiki/Q4680719","display_name":"Adaptive beamformer","level":3,"score":0.4531760513782501},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4335954487323761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4150727391242981},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3783377408981323},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07744252681732178},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1989314204","https://openalex.org/W2039716246","https://openalex.org/W2148613904","https://openalex.org/W2158143227","https://openalex.org/W2168729028","https://openalex.org/W2181607856","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2289480995","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2407277936","https://openalex.org/W2517616541","https://openalex.org/W2559260703","https://openalex.org/W2592384597","https://openalex.org/W2620717980","https://openalex.org/W2699350432","https://openalex.org/W2775641139","https://openalex.org/W2962894366","https://openalex.org/W2963301902","https://openalex.org/W2963399332","https://openalex.org/W6647660671","https://openalex.org/W6686045668","https://openalex.org/W6712626118","https://openalex.org/W6739319914","https://openalex.org/W6740246970","https://openalex.org/W6748559479","https://openalex.org/W6766224279"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2769861442","https://openalex.org/W2120442551","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W1982764159","https://openalex.org/W2348931051"],"abstract_inverted_index":{"This":[0],"work":[1],"examines":[2],"acoustic":[3,51],"beamformers":[4],"employing":[5],"neural":[6],"networks":[7],"(NNs)":[8],"for":[9,15,21,105],"mask":[10,34,99],"prediction":[11],"as":[12],"front":[13],"-end":[14],"automatic":[16],"speech":[17],"recognition":[18,61],"(ASR)":[19],"systems":[20],"practical":[22],"scenarios":[23],"like":[24],"voice-enabled":[25],"home":[26],"devices.":[27],"To":[28],"test":[29],"the":[30,33,37,54,69,72,83,115,124],"versatility":[31],"of":[32,53],"predicting":[35],"network,":[36],"system":[38],"is":[39,85],"evaluated":[40],"with":[41],"different":[42,45,50,103],"recording":[43],"hardware,":[44],"microphone":[46],"array":[47],"designs,":[48],"and":[49],"models":[52],"downstream":[55],"ASR":[56],"system.":[57],"Significant":[58],"gains":[59,121],"in":[60,65],"accuracy":[62],"are":[63,112],"obtained":[64],"all":[66],"configurations":[67],"despite":[68],"fact":[70],"that":[71],"NN":[73,84],"had":[74],"been":[75],"trained":[76,86],"on":[77,87],"mismatched":[78],"data.":[79],"Unlike":[80],"previous":[81],"work,":[82],"a":[88,98],"feature":[89],"level":[90],"objective,":[91],"which":[92],"gives":[93],"some":[94],"performance":[95],"advantage":[96],"over":[97],"related":[100],"criterion.":[101],"Furthermore,":[102],"approaches":[104],"realizing":[106],"online,":[107],"or":[108],"adaptive,":[109],"NN-based":[110],"beamforming":[111],"explored,":[113],"where":[114],"online":[116],"algorithms":[117],"still":[118],"show":[119],"significant":[120],"compared":[122],"to":[123],"baseline":[125],"performance.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
