{"id":"https://openalex.org/W2964041317","doi":"https://doi.org/10.1109/slt.2018.8639651","title":"Speaker Selective Beamformer with Keyword Mask Estimation","display_name":"Speaker Selective Beamformer with Keyword Mask Estimation","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2964041317","doi":"https://doi.org/10.1109/slt.2018.8639651","mag":"2964041317"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5109488356","display_name":"Yusuke Kida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Kida","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dung Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dung Tran","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088171135","display_name":"Motoi Omachi","orcid":"https://orcid.org/0000-0002-9159-4371"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motoi Omachi","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100862172","display_name":"Toru Taniguchi","orcid":"https://orcid.org/0000-0003-4984-2025"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toru Taniguchi","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Yahoo Japan Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo Japan Corporation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"528","last_page":"534"},"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":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.8163172006607056},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7659263610839844},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.611038863658905},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5513911247253418},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5319491028785706},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.48567378520965576},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.46238818764686584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4309615194797516},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.41717085242271423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4099327325820923},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1055232584476471},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07178843021392822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8163172006607056},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7659263610839844},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.611038863658905},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5513911247253418},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5319491028785706},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.48567378520965576},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.46238818764686584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4309615194797516},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.41717085242271423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4099327325820923},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1055232584476471},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07178843021392822},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"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/slt.2018.8639651","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1845880232","https://openalex.org/W1985242443","https://openalex.org/W1987906574","https://openalex.org/W2027884847","https://openalex.org/W2070729636","https://openalex.org/W2124149378","https://openalex.org/W2127851351","https://openalex.org/W2143027228","https://openalex.org/W2144763279","https://openalex.org/W2148613904","https://openalex.org/W2168273590","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2401524124","https://openalex.org/W2460742184","https://openalex.org/W2578331995","https://openalex.org/W2749510669","https://openalex.org/W2749659773","https://openalex.org/W2803322398","https://openalex.org/W2891833136","https://openalex.org/W6638690007"],"related_works":["https://openalex.org/W2381242807","https://openalex.org/W2751208925","https://openalex.org/W2347541121","https://openalex.org/W4288804799","https://openalex.org/W3089617106","https://openalex.org/W3032237421","https://openalex.org/W2080951048","https://openalex.org/W3011883280","https://openalex.org/W2390346111","https://openalex.org/W4226029207"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,52,56,61,65,70,82,86,93,100,106,112,126,134],"problem":[4],"of":[5,10,19,111],"automatic":[6],"speech":[7,104],"recognition":[8],"(ASR)":[9],"a":[11,27,46,77],"target":[12,62,87],"speaker":[13,63],"in":[14],"background":[15,67,103],"speech.":[16,68],"The":[17,41,109],"novelty":[18],"our":[20],"approach":[21],"is":[22,31,115],"that":[23,92,125],"we":[24,123],"focus":[25],"on":[26],"wakeup":[28],"keyword,":[29],"which":[30],"usually":[32],"used":[33,74],"for":[34,75,137],"activating":[35],"ASR":[36,120],"systems":[37],"like":[38],"smart":[39],"speakers.":[40],"proposed":[42,113,135],"method":[43,114,136],"firstly":[44],"utilizes":[45],"DNN-based":[47,95],"mask":[48,96],"estimator":[49],"to":[50,80],"separate":[51,99],"mixture":[53,107],"signal":[54,58],"into":[55],"keyword":[57,101],"uttered":[59],"by":[60,133],"and":[64,102,122,140],"remaining":[66],"Then":[69],"separated":[71],"signals":[72],"are":[73,130],"calculating":[76],"beamforming":[78],"filter":[79],"enhance":[81],"subsequent":[83],"utterances":[84],"from":[85,105],"speaker.":[88],"Experimental":[89],"evaluations":[90],"show":[91],"trained":[94],"can":[97],"selectively":[98],"signal.":[108],"effectiveness":[110],"also":[116],"verified":[117],"with":[118],"Japanese":[119],"experiments,":[121],"confirm":[124],"character":[127],"error":[128],"rates":[129],"significantly":[131],"improved":[132],"both":[138],"simulated":[139],"real":[141],"recorded":[142],"test":[143],"sets.":[144]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}