{"id":"https://openalex.org/W4392908986","doi":"https://doi.org/10.1109/icassp48485.2024.10446934","title":"Leveraging Sound Localization to Improve Continuous Speaker Separation","display_name":"Leveraging Sound Localization to Improve Continuous Speaker Separation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392908986","doi":"https://doi.org/10.1109/icassp48485.2024.10446934"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5073861062","display_name":"Hassan Taherian","orcid":"https://orcid.org/0000-0002-7548-3081"},"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":true,"raw_author_name":"Hassan Taherian","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"],"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Meta Reality Labs,USA","Meta Reality Labs, USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102789202","display_name":"Daniel D.E. Wong","orcid":"https://orcid.org/0000-0002-7781-1149"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Wong","raw_affiliation_strings":["Meta Reality Labs,USA","Meta Reality Labs, USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs,USA","Meta Reality Labs, USA"],"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"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","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"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"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073861062"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.8612,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91148756,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"621","last_page":"625"},"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":0.9994999766349792,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.7511593103408813},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7364518642425537},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6720278263092041},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6253198981285095},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.575188159942627},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5516517758369446},{"id":"https://openalex.org/keywords/mimo","display_name":"MIMO","score":0.5503227710723877},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5299918055534363},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.43145155906677246},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10686185956001282},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09884092211723328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511593103408813},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7364518642425537},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6720278263092041},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6253198981285095},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.575188159942627},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5516517758369446},{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.5503227710723877},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5299918055534363},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.43145155906677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10686185956001282},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09884092211723328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2046317813","https://openalex.org/W2069681747","https://openalex.org/W2117678320","https://openalex.org/W2568308529","https://openalex.org/W2611943505","https://openalex.org/W2701869962","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2897977894","https://openalex.org/W2982456909","https://openalex.org/W3016232124","https://openalex.org/W3081461453","https://openalex.org/W3081729342","https://openalex.org/W3094831814","https://openalex.org/W3104757150","https://openalex.org/W3111598519","https://openalex.org/W3113518618","https://openalex.org/W3132830522","https://openalex.org/W3163208914","https://openalex.org/W3163842642","https://openalex.org/W3171278394","https://openalex.org/W3197097128","https://openalex.org/W3210134537","https://openalex.org/W4210402803","https://openalex.org/W4224920409","https://openalex.org/W4226491018","https://openalex.org/W4313417891","https://openalex.org/W4375869047","https://openalex.org/W4385756463","https://openalex.org/W4385822256","https://openalex.org/W4390660238","https://openalex.org/W6769802879"],"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":{"Continuous":[0],"speaker":[1,42,47,60,75,101,130],"separation":[2,61,90,131],"aims":[3],"to":[4,28,95],"separate":[5],"overlapping":[6],"speakers":[7],"in":[8,18],"real-world":[9],"environments":[10],"like":[11,46],"meetings,":[12],"but":[13],"it":[14],"often":[15],"falls":[16],"short":[17],"isolating":[19],"speech":[20,39],"segments":[21],"of":[22,87],"a":[23,54,85],"single":[24],"speaker.":[25],"This":[26,51,70],"leads":[27],"split":[29],"signals":[30],"that":[31,105,121],"adversely":[32],"affect":[33],"downstream":[34],"applications":[35],"such":[36],"as":[37,84],"automatic":[38],"recognition":[40],"and":[41,99],"diarization.":[43],"Existing":[44],"solutions":[45],"counting":[48],"have":[49],"limitations.":[50],"paper":[52],"presents":[53],"novel":[55],"multi-channel":[56],"approach":[57,72,107,124],"for":[58],"continuous":[59],"based":[62],"on":[63,115],"multi-input":[64],"multi-output":[65],"(MIMO)":[66],"complex":[67],"spectral":[68],"mapping.":[69],"MIMO":[71,89],"enables":[73],"robust":[74],"localization":[76,83],"by":[77],"preserving":[78],"inter-channel":[79],"phase":[80],"relations.":[81],"Speaker":[82],"byproduct":[86],"the":[88,116,122],"model":[91],"is":[92],"then":[93],"used":[94],"identify":[96],"single-talker":[97],"frames":[98],"reduce":[100],"splitting.":[102],"We":[103],"demonstrate":[104],"this":[106],"achieves":[108],"superior":[109],"frame-level":[110],"sound":[111],"localization.":[112],"Systematic":[113],"experiments":[114],"LibriCSS":[117],"dataset":[118],"further":[119],"show":[120],"proposed":[123],"outperforms":[125],"other":[126],"methods,":[127],"advancing":[128],"state-of-the-art":[129],"performance.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}