{"id":"https://openalex.org/W4319862697","doi":"https://doi.org/10.1109/slt54892.2023.10023280","title":"Low-Latency Speech Separation Guided Diarization for Telephone Conversations","display_name":"Low-Latency Speech Separation Guided Diarization for Telephone Conversations","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862697","doi":"https://doi.org/10.1109/slt54892.2023.10023280"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023280","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 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/A5040930642","display_name":"Giovanni Morrone","orcid":"https://orcid.org/0000-0003-2163-1779"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Morrone","raw_affiliation_strings":["Università Politecnica delle Marche,Ancona,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Ancona,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Università Politecnica delle Marche,Ancona,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Ancona,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004777817","display_name":"Desh Raj","orcid":"https://orcid.org/0000-0002-5038-9400"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Desh Raj","raw_affiliation_strings":["Johns Hopkins University,Baltimore,USA","Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041034031","display_name":"Luca Serafini","orcid":"https://orcid.org/0000-0001-7657-4471"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Serafini","raw_affiliation_strings":["Università Politecnica delle Marche,Ancona,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Ancona,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062391550","display_name":"Enrico Zovato","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]},{"id":"https://openalex.org/I4210109975","display_name":"Provincia Autonoma di Trento","ror":"https://ror.org/017e99q89","country_code":"IT","type":"government","lineage":["https://openalex.org/I4210109975"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Zovato","raw_affiliation_strings":["PerVoice S.p.A.,Trento,Italy","PerVoice S.p.A., Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"PerVoice S.p.A.,Trento,Italy","institution_ids":["https://openalex.org/I193223587","https://openalex.org/I4210109975"]},{"raw_affiliation_string":"PerVoice S.p.A., Trento, Italy","institution_ids":["https://openalex.org/I4210109975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066363315","display_name":"Alessio Brutti","orcid":"https://orcid.org/0000-0003-4146-3071"},"institutions":[{"id":"https://openalex.org/I2277624104","display_name":"Fondazione Bruno Kessler","ror":"https://ror.org/01j33xk10","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2277624104"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessio Brutti","raw_affiliation_strings":["Fondazione Bruno Kessler,Trento,Italy","Fondazione Bruno Kessler, Trento, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Bruno Kessler,Trento,Italy","institution_ids":["https://openalex.org/I2277624104"]},{"raw_affiliation_string":"Fondazione Bruno Kessler, Trento, Italy","institution_ids":["https://openalex.org/I2277624104"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034253968","display_name":"Stefano Squartini","orcid":"https://orcid.org/0000-0001-9374-0128"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Squartini","raw_affiliation_strings":["Università Politecnica delle Marche,Ancona,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Ancona,Italy","institution_ids":["https://openalex.org/I122534668"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5521,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92277947,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"641","last_page":"646"},"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":0.9998999834060669,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9049012064933777},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7910791635513306},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7529174089431763},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6419357061386108},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5792772173881531},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.511681318283081},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4687595069408417},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.45351213216781616},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4490707814693451},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4210863411426544},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.37257274985313416},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33021634817123413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18383491039276123},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13001582026481628},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11298057436943054}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9049012064933777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7910791635513306},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7529174089431763},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6419357061386108},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5792772173881531},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.511681318283081},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4687595069408417},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.45351213216781616},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4490707814693451},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4210863411426544},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.37257274985313416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33021634817123413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18383491039276123},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13001582026481628},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11298057436943054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023280","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023280","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1522301498","https://openalex.org/W2081074144","https://openalex.org/W2125336414","https://openalex.org/W2288817436","https://openalex.org/W2638067502","https://openalex.org/W2734774145","https://openalex.org/W2952218014","https://openalex.org/W2963470929","https://openalex.org/W2964058413","https://openalex.org/W2972449503","https://openalex.org/W3008357631","https://openalex.org/W3010196324","https://openalex.org/W3015199127","https://openalex.org/W3015780472","https://openalex.org/W3015783745","https://openalex.org/W3016031604","https://openalex.org/W3020336359","https://openalex.org/W3025260599","https://openalex.org/W3033627755","https://openalex.org/W3094831814","https://openalex.org/W3095212884","https://openalex.org/W3095717210","https://openalex.org/W3099330747","https://openalex.org/W3105031100","https://openalex.org/W3128434617","https://openalex.org/W3128688470","https://openalex.org/W3147778289","https://openalex.org/W3162347631","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3197762688","https://openalex.org/W3203236698","https://openalex.org/W3212886388","https://openalex.org/W4225792560","https://openalex.org/W4281715917","https://openalex.org/W6603931906","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6678809451","https://openalex.org/W6738904159","https://openalex.org/W6768815455","https://openalex.org/W6773628751","https://openalex.org/W6774558098","https://openalex.org/W6779069803","https://openalex.org/W6784464189","https://openalex.org/W6785552926","https://openalex.org/W6789114347","https://openalex.org/W6790297703","https://openalex.org/W6837816658"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"In":[0,39],"this":[1],"paper,":[2],"we":[3,41,49],"carry":[4],"out":[5],"an":[6,107],"analysis":[7],"on":[8,34,69,93,106],"the":[9,25,57,127,143],"use":[10],"of":[11,61,109],"speech":[12,45,136],"separation":[13,46,80],"guided":[14],"diarization":[15,22,82,101],"(SSGD)":[16],"in":[17],"telephone":[18],"conversations.":[19],"SSGD":[20,63,86],"performs":[21],"by":[23],"separating":[24],"speakers":[26],"signals":[27,129],"and":[28,76,81,113],"then":[29],"applying":[30],"voice":[31],"activity":[32],"detection":[33],"each":[35],"estimated":[36],"speaker":[37],"signal.":[38],"particular,":[40],"compare":[42],"two":[43,70],"low-latency":[44],"models.":[47],"Moreover,":[48],"show":[50,125],"a":[51,62,135],"post-processing":[52],"algorithm":[53],"that":[54,126],"significantly":[55],"reduces":[56],"false":[58],"alarm":[59],"errors":[60],"pipeline.":[64],"We":[65,123],"perform":[66],"our":[67,85],"experiments":[68],"datasets:":[71],"Fisher":[72],"Corpus":[73],"Part":[74],"1":[75],"CALLHOME,":[77],"evaluating":[78],"both":[79],"metrics.":[83],"Notably,":[84],"DPRNN-based":[87],"online":[88],"model":[89],"achieves":[90],"11.1%":[91],"DER":[92],"CALL-HOME,":[94],"comparable":[95],"with":[96,139],"most":[97],"state-of-the-art":[98],"end-to-end":[99],"neural":[100],"models":[102],"despite":[103],"being":[104],"trained":[105],"order":[108],"magnitude":[110],"less":[111],"data":[112],"having":[114],"considerably":[115],"lower":[116],"latency,":[117],"i.e.,":[118],"0.1":[119],"vs.":[120],"10":[121],"seconds.":[122],"also":[124],"separated":[128],"can":[130],"be":[131],"readily":[132],"fed":[133],"to":[134,142],"recognition":[137],"back-end":[138],"performance":[140],"close":[141],"oracle":[144],"source":[145],"signals.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}