{"id":"https://openalex.org/W3182358018","doi":"https://doi.org/10.1109/icassp43922.2022.9746896","title":"Localization based Sequential Grouping for Continuous Speech Separation","display_name":"Localization based Sequential Grouping for Continuous Speech Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3182358018","doi":"https://doi.org/10.1109/icassp43922.2022.9746896","mag":"3182358018"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746896","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),USA","Mitsubishi Electric Research Laboratories (MERL), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"285"},"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":0.9995999932289124,"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":0.9994000196456909,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8655394315719604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7599246501922607},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7472938895225525},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6085456609725952},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5893775820732117},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.55216383934021},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.45607641339302063},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4516455829143524},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3881995975971222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34027814865112305},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3331974148750305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11881205439567566},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.07372555136680603}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8655394315719604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7599246501922607},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7472938895225525},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6085456609725952},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5893775820732117},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.55216383934021},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.45607641339302063},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4516455829143524},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3881995975971222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34027814865112305},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3331974148750305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11881205439567566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.07372555136680603},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746896","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W1555217905","https://openalex.org/W2081074144","https://openalex.org/W2096259168","https://openalex.org/W2132056833","https://openalex.org/W2133845853","https://openalex.org/W2140672401","https://openalex.org/W2148613904","https://openalex.org/W2168379380","https://openalex.org/W2221409856","https://openalex.org/W2701869962","https://openalex.org/W2734774145","https://openalex.org/W2803322398","https://openalex.org/W2884797218","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2897977894","https://openalex.org/W2900212944","https://openalex.org/W2917174945","https://openalex.org/W2952752702","https://openalex.org/W2962866211","https://openalex.org/W2972949456","https://openalex.org/W3007256793","https://openalex.org/W3008283340","https://openalex.org/W3015679215","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3016244460","https://openalex.org/W3016400019","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3032514799","https://openalex.org/W3048833027","https://openalex.org/W3094831814","https://openalex.org/W3114363279","https://openalex.org/W3125596972","https://openalex.org/W3151596526","https://openalex.org/W3162315798","https://openalex.org/W3162347631","https://openalex.org/W3163019736","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3212886388","https://openalex.org/W3216920799","https://openalex.org/W6674325791","https://openalex.org/W6679681082","https://openalex.org/W6680492576","https://openalex.org/W6688843265","https://openalex.org/W6752148239","https://openalex.org/W6754496211","https://openalex.org/W6755054534","https://openalex.org/W6773628751","https://openalex.org/W6773721078","https://openalex.org/W6774249064","https://openalex.org/W6774803370","https://openalex.org/W6782142667","https://openalex.org/W6784351597","https://openalex.org/W6787577498","https://openalex.org/W6788275255","https://openalex.org/W6790122275","https://openalex.org/W6790828191"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"robust":[3],"speaker":[4,11,16,53],"localization":[5],"for":[6,48],"continuous":[7],"speech":[8,108],"separation":[9,77,95],"and":[10,32,52,92,106],"diarization,":[12],"where":[13],"we":[14,73],"use":[15],"directions":[17],"to":[18,79],"group":[19,93],"non-contiguous":[20],"segments":[21],"of":[22,40,66,88,118],"the":[23,38,60,83,86,94,101,112,116,119],"same":[24],"speaker.":[25],"Assuming":[26],"that":[27],"speakers":[28],"do":[29],"not":[30],"move":[31],"are":[33],"located":[34],"in":[35,59],"different":[36],"directions,":[37],"direction":[39],"arrival":[41],"(DOA)":[42],"information":[43],"provides":[44],"an":[45],"informative":[46],"cue":[47],"accurate":[49],"sequential":[50],"grouping":[51],"diarization.":[54],"Our":[55],"system":[56],"is":[57],"block-online":[58],"following":[61],"sense.":[62],"Given":[63],"a":[64,75],"block":[65],"frames":[67],"with":[68],"at":[69],"most":[70],"two":[71],"speakers,":[72,84],"apply":[74],"two-speaker":[76],"model":[78],"separate":[80],"(and":[81],"enhance)":[82],"estimate":[85],"DOA":[87,102],"each":[89],"separated":[90],"speaker,":[91],"results":[96,110],"across":[97],"blocks":[98],"based":[99],"on":[100,111],"estimates.":[103],"Speaker":[104],"diarization":[105],"speaker-attributed":[107],"recognition":[109],"LibriCSS":[113],"corpus":[114],"demonstrate":[115],"effectiveness":[117],"proposed":[120],"algorithm.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}