{"id":"https://openalex.org/W4319663602","doi":"https://doi.org/10.1109/access.2023.3243690","title":"Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection","display_name":"Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319663602","doi":"https://doi.org/10.1109/access.2023.3243690"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3243690","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3243690","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041133.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041133.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"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":true,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation, Yokosuka, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049917170","display_name":"Hiroshi Sat\u014d","orcid":"https://orcid.org/0000-0002-5899-1340"},"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":"Hiroshi Sato","raw_affiliation_strings":["NTT Corporation, Yokosuka, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","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, Yokosuka, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka, 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, Yokosuka, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, Yokosuka, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5087290011"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.9202,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88178709,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"13906","last_page":"13917"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9997000098228455,"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":0.817468523979187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7873002290725708},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7535978555679321},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.6034677624702454},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6009240746498108},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.568409264087677},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4163796901702881},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38422712683677673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35368409752845764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34558844566345215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.817468523979187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7873002290725708},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7535978555679321},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6034677624702454},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6009240746498108},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.568409264087677},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4163796901702881},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38422712683677673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35368409752845764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34558844566345215},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2023.3243690","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3243690","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041133.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1a76227eab2c4224b8ccaede592b14bf","is_oa":true,"landing_page_url":"https://doaj.org/article/1a76227eab2c4224b8ccaede592b14bf","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 13906-13917 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3243690","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3243690","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041133.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319663602.pdf","grobid_xml":"https://content.openalex.org/works/W4319663602.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W2064675550","https://openalex.org/W2160815625","https://openalex.org/W2559809918","https://openalex.org/W2884797218","https://openalex.org/W2936774411","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2964084166","https://openalex.org/W2972362771","https://openalex.org/W2972474532","https://openalex.org/W2973054998","https://openalex.org/W3008003372","https://openalex.org/W3015190365","https://openalex.org/W3015636705","https://openalex.org/W3015927303","https://openalex.org/W3094806148","https://openalex.org/W3096090308","https://openalex.org/W3096518646","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3105928222","https://openalex.org/W3109079702","https://openalex.org/W3161158930","https://openalex.org/W3161354387","https://openalex.org/W3161873870","https://openalex.org/W3162444624","https://openalex.org/W3162847598","https://openalex.org/W3186652349","https://openalex.org/W3198254488","https://openalex.org/W3198442913","https://openalex.org/W3198575250","https://openalex.org/W3198667862","https://openalex.org/W4210663600","https://openalex.org/W4221153233","https://openalex.org/W4224920108","https://openalex.org/W4226098957","https://openalex.org/W4226491018","https://openalex.org/W4283074506","https://openalex.org/W4296070363","https://openalex.org/W4297841877","https://openalex.org/W6600284362","https://openalex.org/W6601563604","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6638523607","https://openalex.org/W6638749077"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,25,48,64,82,136],"recognition":[2,30,65,83,117,141],"of":[3,10,39,49,133],"a":[4,14,69,80,101,134,140],"target":[5,41,51,92,135],"speaker":[6,52,93],"in":[7,99],"the":[8,29,37,40,47,50,91],"presence":[9],"interfering":[11],"speakers":[12],"remains":[13],"challenging":[15],"issue.":[16],"One":[17],"approach":[18],"to":[19,73,88,109,129],"tackle":[20],"this":[21,57],"problem":[22],"is":[23,94],"target-speaker":[24,63,81,111],"recognition,":[26],"which":[27],"conditions":[28],"process":[31],"on":[32,68],"an":[33,61],"embedding":[34],"that":[35,122],"characterizes":[36],"voice":[38],"speaker.":[42],"This":[43],"enables":[44],"recognizing":[45],"only":[46],"while":[53,143],"ignoring":[54],"interferences.":[55],"In":[56],"work,":[58],"we":[59],"propose":[60],"end-to-end":[62,125],"system":[66,84,126],"based":[67],"neural":[70],"transducer":[71],"architecture":[72],"allow":[74,110],"streaming":[75,149],"and":[76,96,106,139,147],"on-device":[77],"recognition.":[78],"Moreover,":[79],"should":[85],"be":[86],"able":[87],"detect":[89],"when":[90],"inactive":[95],"output":[97],"nothing":[98],"such":[100],"case.":[102],"We":[103,119],"introduce":[104],"training":[105],"decoding":[107],"schemes":[108],"activity":[112],"detection":[113],"within":[114],"our":[115,123],"proposed":[116,124],"system.":[118],"confirm":[120],"experimentally":[121],"performs":[127],"competitively":[128],"conventional":[130],"cascade":[131],"approaches":[132],"extraction":[137],"module":[138,142],"reducing":[144],"computation":[145],"costs":[146],"allowing":[148],"decoding.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}