{"id":"https://openalex.org/W4403126659","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694508","title":"Low-Latency Single-Microphone Speaker Separation with Temporal Convolutional Networks Using Speaker Representations","display_name":"Low-Latency Single-Microphone Speaker Separation with Temporal Convolutional Networks Using Speaker Representations","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403126659","doi":"https://doi.org/10.1109/iwaenc61483.2024.10694508"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10694508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5107744395","display_name":"Boris Rubenchik","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Boris Rubenchik","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008128887","display_name":"Elior Hadad","orcid":"https://orcid.org/0000-0002-5238-5868"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Elior Hadad","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039310976","display_name":"Eli Tzirkel","orcid":null},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Eli Tzirkel","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University,Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053007211","display_name":"Ethan Fetaya","orcid":"https://orcid.org/0000-0003-3125-1665"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ethan Fetaya","raw_affiliation_strings":["General Motors Technical Center,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"General Motors Technical Center,Israel","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001052072","display_name":"Sharon Gannot","orcid":"https://orcid.org/0000-0002-2885-170X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Gannot","raw_affiliation_strings":["General Motors Technical Center,Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"General Motors Technical Center,Israel","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20803517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"155","last_page":"159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9905999898910522,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9498999714851379,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7661356329917908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6589388847351074},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6055724024772644},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5943045616149902},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.534206748008728},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.509168803691864},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4414089322090149},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.436549574136734},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4225753843784332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2426014542579651},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10153937339782715},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07617998123168945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661356329917908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6589388847351074},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6055724024772644},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5943045616149902},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.534206748008728},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.509168803691864},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4414089322090149},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.436549574136734},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4225753843784332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2426014542579651},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10153937339782715},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07617998123168945},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10694508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10694508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1991139021","https://openalex.org/W2067295501","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2760103357","https://openalex.org/W2937484199","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2972460025","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015654783","https://openalex.org/W3042857426","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3142910119","https://openalex.org/W3160408143","https://openalex.org/W3163652268","https://openalex.org/W3185109982","https://openalex.org/W3191469971","https://openalex.org/W4233392025","https://openalex.org/W6774995033","https://openalex.org/W6797987982"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"This":[0],"article":[1],"introduces":[2],"a":[3,32,40,57,86,95,103],"novel":[4],"method":[5],"for":[6,43,141],"single-channel":[7],"speaker":[8,24,37,66],"separation,":[9,25],"focusing":[10],"on":[11,116,119],"causal":[12,97],"and":[13,52,80,94,134],"low-latency":[14,36],"inference.":[15],"While":[16],"significant":[17,126],"advancements":[18],"have":[19],"been":[20],"recently":[21],"made":[22],"in":[23,27,63,84],"especially":[26],"non-causal":[28],"scenarios,":[29],"there":[30],"is":[31],"notable":[33],"gap":[34],"concerning":[35],"separation":[38],"\u2014":[39],"critical":[41],"requirement":[42],"real-time":[44],"conversational":[45],"applications":[46],"like":[47],"phone":[48],"calls,":[49,51],"video":[50],"human-machine":[53],"interaction.":[54],"We":[55],"propose":[56],"two-stage":[58,123],"solution":[59,124,139],"that":[60],"leverages":[61],"initial-separation":[62],"conjunction":[64],"with":[65],"representation-driven":[67],"refinement.":[68],"To":[69],"assess":[70],"the":[71,107,131],"effectiveness":[72],"of":[73,91,106,109],"our":[74],"method,":[75],"we":[76,100],"conducted":[77],"extensive":[78],"experiments":[79],"examined":[81],"its":[82],"performance":[83,127],"both":[85],"very":[87],"low":[88],"algorithmic":[89],"latency":[90],"16":[92],"milliseconds":[93],"fully":[96],"model.":[98],"Additionally,":[99],"delve":[101],"into":[102],"detailed":[104],"analysis":[105],"composition":[108],"datasets":[110],"derived":[111],"from":[112],"WSJ0,":[113],"shedding":[114],"light":[115],"their":[117],"impact":[118],"model":[120,133],"evaluation.":[121],"Our":[122],"demonstrates":[125],"enhancements":[128],"compared":[129],"to":[130],"baseline":[132],"offers":[135],"an":[136],"easily":[137],"deployable":[138],"suitable":[140],"edge":[142],"devices.":[143]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}