{"id":"https://openalex.org/W4316660723","doi":"https://doi.org/10.1109/taslp.2023.3237172","title":"Mask-Based Neural Beamforming for Moving Speakers With Self-Attention-Based Tracking","display_name":"Mask-Based Neural Beamforming for Moving Speakers With Self-Attention-Based Tracking","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4316660723","doi":"https://doi.org/10.1109/taslp.2023.3237172"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3237172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237172","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2519-2032","affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"raw_orcid":"https://orcid.org/0000-0002-5175-7834","affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation, Chiyoda-ku, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4363-4305","affiliations":[{"raw_affiliation_string":"NTT Corporation, Chiyoda-ku, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":5.0452,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96425587,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"835","last_page":"848"},"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/T11698","display_name":"Underwater Acoustics Research","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9972000122070312,"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/beamforming","display_name":"Beamforming","score":0.8537671566009521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7945120334625244},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5826735496520996},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5491634607315063},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49422433972358704},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4607582688331604},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4571130573749542},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4488275349140167},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4128651022911072},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36731815338134766},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33471089601516724},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1931849718093872},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11476835608482361},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10961282253265381},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10581445693969727}],"concepts":[{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.8537671566009521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7945120334625244},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5826735496520996},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5491634607315063},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49422433972358704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4607582688331604},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4571130573749542},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4488275349140167},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4128651022911072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36731815338134766},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33471089601516724},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1931849718093872},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11476835608482361},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10961282253265381},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10581445693969727},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3237172","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3237172","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1555217905","https://openalex.org/W1976805820","https://openalex.org/W1982728343","https://openalex.org/W2009153891","https://openalex.org/W2024490156","https://openalex.org/W2042860487","https://openalex.org/W2043216213","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2113638573","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2135823751","https://openalex.org/W2141998673","https://openalex.org/W2147665979","https://openalex.org/W2158143227","https://openalex.org/W2160815625","https://openalex.org/W2168729028","https://openalex.org/W2289394825","https://openalex.org/W2398042854","https://openalex.org/W2398972335","https://openalex.org/W2400339399","https://openalex.org/W2514741789","https://openalex.org/W2516857479","https://openalex.org/W2517616541","https://openalex.org/W2539508298","https://openalex.org/W2586584460","https://openalex.org/W2803583024","https://openalex.org/W2884797218","https://openalex.org/W2885219692","https://openalex.org/W2891997645","https://openalex.org/W2892009249","https://openalex.org/W2898268964","https://openalex.org/W2905402910","https://openalex.org/W2937581095","https://openalex.org/W2938386503","https://openalex.org/W2944332669","https://openalex.org/W2952218014","https://openalex.org/W2962892438","https://openalex.org/W2964058413","https://openalex.org/W2972693890","https://openalex.org/W2998378360","https://openalex.org/W3021261768","https://openalex.org/W3086154751","https://openalex.org/W3089913183","https://openalex.org/W3099330747","https://openalex.org/W3102937397","https://openalex.org/W3104196160","https://openalex.org/W3127217413","https://openalex.org/W3152963531","https://openalex.org/W3160588708","https://openalex.org/W3162341667","https://openalex.org/W3196360884","https://openalex.org/W3198730349","https://openalex.org/W4249052411","https://openalex.org/W4312356750","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6631362777"],"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/W3124036039","https://openalex.org/W2130785056","https://openalex.org/W2132841313"],"abstract_inverted_index":{"Beamforming":[0],"is":[1],"a":[2,14,85,107,136,158,172],"powerful":[3],"tool":[4],"designed":[5],"to":[6,38,83,125,210],"enhance":[7],"speech":[8],"signals":[9],"from":[10],"the":[11,18,28,50,70,95,123,128,204],"direction":[12],"of":[13,27,44,72,94,109,122,141,206],"target":[15],"source.":[16],"Computing":[17],"beamforming":[19,46,74,189],"filter":[20],"requires":[21],"estimating":[22],"spatial":[23],"covariance":[24],"matrices":[25],"(SCMs)":[26],"source":[29,193,211],"and":[30,138],"noise":[31],"signals.":[32],"Time-frequency":[33],"masks":[34],"are":[35],"often":[36,57],"used":[37],"compute":[39],"these":[40,100,143],"SCMs.":[41,96],"Most":[42],"studies":[43],"mask-based":[45,73,207],"have":[47],"assumed":[48],"that":[49,99,161,182],"sources":[51,56],"do":[52],"not":[53,150],"move.":[54],"However,":[55],"move":[58],"in":[59,127,152,191,199],"practice,":[60],"which":[61,88,119],"causes":[62],"performance":[63,190,198],"degradation.":[64],"In":[65],"this":[66,170],"paper,":[67],"we":[68],"address":[69],"problem":[71],"for":[75,166],"moving":[76,86,192],"sources.":[77],"We":[78,97,155,168,179],"first":[79],"review":[80],"classical":[81],"approaches":[82,101],"tracking":[84],"source,":[87],"perform":[89],"online":[90],"or":[91,132],"blockwise":[92,133],"computation":[93,134],"show":[98,180],"can":[102,186],"be":[103],"interpreted":[104],"as":[105],"computing":[106,142],"sum":[108],"instantaneous":[110],"SCMs":[111],"weighted":[112],"by":[113],"attention":[114,144,164],"weights.":[115],"These":[116],"weights":[117,145,165],"indicate":[118],"time":[120],"frames":[121],"signal":[124],"consider":[126],"SCM":[129],"computation.":[130],"Online":[131],"assumes":[135],"heuristic":[137],"deterministic":[139],"way":[140],"that,":[146],"although":[147],"simple,":[148],"may":[149],"result":[151],"optimal":[153,163],"performance.":[154],"thus":[156,202],"introduce":[157],"learning-based":[159],"framework":[160,185],"computes":[162],"beamforming.":[167],"achieve":[169],"using":[171],"neural":[173],"network":[174],"implemented":[175],"with":[176],"self-attention":[177],"layers.":[178],"experimentally":[181],"our":[183],"proposed":[184],"greatly":[187],"improve":[188],"situations":[194],"while":[195],"maintaining":[196],"high":[197],"non-moving":[200],"situations,":[201],"enabling":[203],"development":[205],"beamformers":[208],"robust":[209],"movements.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}