{"id":"https://openalex.org/W3140651083","doi":"https://doi.org/10.1109/slt48900.2021.9383510","title":"Block-Online Guided Source Separation","display_name":"Block-Online Guided Source Separation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3140651083","doi":"https://doi.org/10.1109/slt48900.2021.9383510","mag":"3140651083"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044818016","display_name":"Yusuke Fujita","orcid":"https://orcid.org/0000-0002-6523-8146"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Fujita","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076987349","display_name":"Kenji Nagamatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenji Nagamatsu","raw_affiliation_strings":["Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65143321"],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4722529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"236","last_page":"242"},"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":0.9987000226974487,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8100839853286743},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7467620372772217},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6964278817176819},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6396193504333496},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5762485861778259},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5493086576461792},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.5388102531433105},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5279577970504761},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44394975900650024},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34368863701820374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09703779220581055},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08915510773658752}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100839853286743},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7467620372772217},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6964278817176819},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6396193504333496},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5762485861778259},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5493086576461792},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.5388102531433105},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5279577970504761},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44394975900650024},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34368863701820374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09703779220581055},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08915510773658752},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383510","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":47,"referenced_works":["https://openalex.org/W1544785557","https://openalex.org/W1994065850","https://openalex.org/W2158143227","https://openalex.org/W2164502538","https://openalex.org/W2563666542","https://openalex.org/W2586584460","https://openalex.org/W2606300880","https://openalex.org/W2746574320","https://openalex.org/W2750380122","https://openalex.org/W2785745830","https://openalex.org/W2889503488","https://openalex.org/W2889664202","https://openalex.org/W2890553422","https://openalex.org/W2891984996","https://openalex.org/W2892163332","https://openalex.org/W2896538040","https://openalex.org/W2900091068","https://openalex.org/W2900212944","https://openalex.org/W2937581095","https://openalex.org/W2952752702","https://openalex.org/W2952992734","https://openalex.org/W2963197115","https://openalex.org/W2964272710","https://openalex.org/W2972439411","https://openalex.org/W2972492143","https://openalex.org/W3004309045","https://openalex.org/W3004597053","https://openalex.org/W3015372568","https://openalex.org/W3015974384","https://openalex.org/W3016094953","https://openalex.org/W3016257794","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3033930274","https://openalex.org/W3094893851","https://openalex.org/W3097700828","https://openalex.org/W3128434617","https://openalex.org/W3131736947","https://openalex.org/W3132613748","https://openalex.org/W3132806173","https://openalex.org/W4237168004","https://openalex.org/W4294619417","https://openalex.org/W6747158283","https://openalex.org/W6766380642","https://openalex.org/W6774639334","https://openalex.org/W6778996958","https://openalex.org/W6779253965"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,12,44,63,169],"block-online":[3],"algorithm":[4,72,115,176,187],"of":[5,23,27,47,57,82,125,154],"guided":[6],"source":[7],"separation":[8,14],"(GSS).":[9],"GSS":[10,35,68,186],"is":[11,51,61,69,194],"speech":[13],"method":[15],"that":[16,34,65,74,173],"uses":[17],"diarization":[18],"information":[19],"to":[20,54,79,106,116],"update":[21,107],"parameters":[22,153],"the":[24,55,66,80,83,86,101,108,111,114,137,152,165,174,179,183],"generative":[25],"model":[26],"observation":[28],"signals.":[29],"Previous":[30],"studies":[31],"have":[32],"shown":[33],"performs":[36],"well":[37],"in":[38,100,157],"multi-talker":[39],"scenarios.":[40],"However,":[41],"it":[42,75],"requires":[43],"large":[45],"amount":[46],"calculation":[48,147],"time,":[49],"which":[50,193],"an":[52,70],"obstacle":[53],"deployment":[56],"online":[58],"applications.":[59,198],"It":[60,144],"also":[62,145],"problem":[64],"offline":[67,185],"utterance-wise":[71],"so":[73],"produces":[76],"latency":[77,132],"according":[78],"length":[81,139],"utterance.":[84],"With":[85],"proposed":[87,175],"algorithm,":[88],"block-wise":[89],"input":[90],"samples":[91],"and":[92,104,130,160,168],"corresponding":[93],"time":[94],"annotations":[95],"are":[96],"concatenated":[97],"with":[98,189],"those":[99],"preceding":[102],"context":[103,112],"used":[105],"parameters.":[109],"Using":[110],"enables":[113],"estimate":[117],"time-frequency":[118],"masks":[119],"accurately":[120],"only":[121,151],"from":[122],"one":[123],"iteration":[124],"optimization":[126],"for":[127,196],"each":[128,158],"block,":[129],"its":[131,161],"does":[133],"not":[134],"depend":[135],"on":[136,164],"utterance":[138],"but":[140,188],"predetermined":[141],"block":[142,159],"length.":[143],"reduces":[146],"cost":[148],"by":[149],"updating":[150],"active":[155],"speakers":[156],"context.":[162],"Evaluation":[163],"CHiME-6":[166],"corpus":[167,171],"meeting":[170],"showed":[172],"achieved":[177],"almost":[178],"same":[180],"performance":[181],"as":[182],"conventional":[184],"32x":[190],"faster":[191],"calculation,":[192],"sufficient":[195],"real-time":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}