{"id":"https://openalex.org/W4392902932","doi":"https://doi.org/10.1109/icassp48485.2024.10446666","title":"Enhancing Low-Latency Speaker Diarization with Spatial Dictionary Learning","display_name":"Enhancing Low-Latency Speaker Diarization with Spatial Dictionary Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902932","doi":"https://doi.org/10.1109/icassp48485.2024.10446666"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446666","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/A5101543632","display_name":"Weiguang Chen","orcid":"https://orcid.org/0000-0002-7945-3197"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weiguang Chen","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China","College of Computer Science and Electronic Engineering, Hunan University, China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001349788","display_name":"Tran The Anh","orcid":"https://orcid.org/0000-0003-4751-4570"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran The Anh","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681425","display_name":"Xionghu Zhong","orcid":"https://orcid.org/0000-0002-7533-2347"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xionghu Zhong","raw_affiliation_strings":["Hunan University,College of Computer Science and Electronic Engineering,China","College of Computer Science and Electronic Engineering, Hunan University, China"],"affiliations":[{"raw_affiliation_string":"Hunan University,College of Computer Science and Electronic Engineering,China","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101543632"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.7471,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65080045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11371","last_page":"11375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9922000169754028,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9184131026268005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7884954214096069},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6437703371047974},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6284904479980469},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6001659035682678},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4976101219654083},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44393399357795715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41462546586990356},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3691900372505188},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.24389946460723877},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08995410799980164},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07305127382278442}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9184131026268005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7884954214096069},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6437703371047974},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6284904479980469},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6001659035682678},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4976101219654083},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44393399357795715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41462546586990356},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3691900372505188},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.24389946460723877},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08995410799980164},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07305127382278442},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446666","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":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1609132941","https://openalex.org/W2148613904","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2638067502","https://openalex.org/W2963470929","https://openalex.org/W2963843276","https://openalex.org/W2989790778","https://openalex.org/W3008357631","https://openalex.org/W3017474798","https://openalex.org/W3025260599","https://openalex.org/W3042558177","https://openalex.org/W3095212884","https://openalex.org/W3097777922","https://openalex.org/W3117396592","https://openalex.org/W3132830522","https://openalex.org/W3157070662","https://openalex.org/W3197801171","https://openalex.org/W3198482860","https://openalex.org/W3203417382","https://openalex.org/W3207834622","https://openalex.org/W3212886388","https://openalex.org/W4221164375","https://openalex.org/W4224916247","https://openalex.org/W4224916733","https://openalex.org/W4297841423","https://openalex.org/W4313316127","https://openalex.org/W4375869289","https://openalex.org/W4396713940"],"related_works":["https://openalex.org/W4384929466","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W4392375438","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4360103953","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463"],"abstract_inverted_index":{"This":[0,30],"study":[1],"proposes":[2],"a":[3,12,43,74,85],"low-latency":[4],"online":[5,39,93],"speaker":[6,58],"diarization":[7,40,78,101],"framework.":[8],"Specifically,":[9],"we":[10],"design":[11],"spatial":[13,23,65],"dictionary":[14],"learning":[15,25],"module":[16],"shared":[17],"across":[18,81],"different":[19],"frequency":[20,28],"bands,":[21],"enabling":[22],"feature":[24],"at":[26],"each":[27],"bin.":[29],"contributes":[31],"to":[32,48,91,106],"reducing":[33],"the":[34,38,53,70,107,112],"latency":[35],"constraints":[36],"of":[37,88,111],"system.":[41],"Additionally,":[42],"magnitude-weighted":[44],"fusion":[45],"is":[46],"devised":[47],"integrate":[49],"spectral":[50,63],"features.":[51,66],"Consequently,":[52],"system":[54,110],"can":[55],"extract":[56],"discriminative":[57],"embeddings":[59],"by":[60],"simultaneously":[61],"considering":[62],"and":[64,102],"Experimental":[67],"results":[68],"on":[69],"Alimeeting":[71,113],"dataset":[72],"demonstrate":[73],"significant":[75],"improvement":[76,87],"in":[77],"error":[79],"rates":[80],"various":[82],"latencies,":[83],"with":[84],"relative":[86],"45.80%":[89],"compared":[90],"single-channel":[92],"diarization.":[94],"Moreover,":[95],"our":[96],"method":[97],"surpasses":[98],"offline":[99,109],"direction-of-arrival-based":[100],"achieves":[103],"comparable":[104],"performance":[105],"second-ranked":[108],"challenge.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}