{"id":"https://openalex.org/W3203417382","doi":"https://doi.org/10.1109/icassp43922.2022.9746531","title":"Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection","display_name":"Turn-to-Diarize: Online Speaker Diarization Constrained by Transformer Transducer Speaker Turn Detection","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3203417382","doi":"https://doi.org/10.1109/icassp43922.2022.9746531","mag":"3203417382"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746531","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":"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/A5101861591","display_name":"Wei Xia","orcid":"https://orcid.org/0009-0009-4734-6256"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086894713","display_name":"Lu Han","orcid":"https://orcid.org/0000-0002-1120-3220"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Lu","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032868162","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0002-5951-6752"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403998","display_name":"Anshuman Tripathi","orcid":"https://orcid.org/0000-0002-4902-3719"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anshuman Tripathi","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103123086","display_name":"Yiling Huang","orcid":"https://orcid.org/0009-0008-0554-0942"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiling Huang","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez Moreno","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108537573","display_name":"Ha\u015fim Sak","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hasim Sak","raw_affiliation_strings":["Google LLC,USA","Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC,USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101861591"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":4.6942,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.96020138,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8077","last_page":"8081"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech 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/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":0.9611514806747437},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7564880847930908},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6663216352462769},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6462424397468567},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5471202731132507},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5149141550064087},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.48979687690734863},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4867415428161621},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3425309658050537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31565171480178833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10715857148170471}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9611514806747437},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7564880847930908},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6663216352462769},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6462424397468567},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5471202731132507},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5149141550064087},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.48979687690734863},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4867415428161621},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3425309658050537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31565171480178833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10715857148170471},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746531","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":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1485222997","https://openalex.org/W1516407653","https://openalex.org/W1635512741","https://openalex.org/W1828163288","https://openalex.org/W1875623881","https://openalex.org/W2038101708","https://openalex.org/W2132914434","https://openalex.org/W2150769028","https://openalex.org/W2513345070","https://openalex.org/W2527729766","https://openalex.org/W2617258110","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2746241180","https://openalex.org/W2750259098","https://openalex.org/W2786458517","https://openalex.org/W2889203268","https://openalex.org/W2890964092","https://openalex.org/W2896538040","https://openalex.org/W2962760690","https://openalex.org/W2962788625","https://openalex.org/W2963227667","https://openalex.org/W2963470929","https://openalex.org/W2972949456","https://openalex.org/W2973127116","https://openalex.org/W2982413405","https://openalex.org/W2992261503","https://openalex.org/W2997419692","https://openalex.org/W3015598461","https://openalex.org/W3016010032","https://openalex.org/W3092122846","https://openalex.org/W3100648197","https://openalex.org/W3105031100","https://openalex.org/W3125596972","https://openalex.org/W3145204487","https://openalex.org/W3160044950","https://openalex.org/W3179294409","https://openalex.org/W3196705076","https://openalex.org/W3197845638","https://openalex.org/W3212886388","https://openalex.org/W4288088457","https://openalex.org/W4294589828","https://openalex.org/W6603931906","https://openalex.org/W6638749077","https://openalex.org/W6745415975","https://openalex.org/W6748447238","https://openalex.org/W6769806307","https://openalex.org/W6784400248"],"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":{"In":[0,14],"this":[1,15],"paper,":[2],"we":[3,17],"present":[4],"a":[5,19,32],"novel":[6],"speaker":[7,25,29,33,44,66,71,79,88],"diarization":[8,50,72],"system":[9,53,84],"for":[10,81],"streaming":[11],"on-device":[12],"applications.":[13],"system,":[16],"use":[18],"transformer":[20],"transducer":[21],"to":[22,62],"detect":[23],"the":[24,42,56,63,92,98],"turns,":[26],"represent":[27],"each":[28],"turn":[30,89],"by":[31],"embedding,":[34],"then":[35],"cluster":[36],"these":[37],"embeddings":[38],"with":[39,47],"constraints":[40],"from":[41],"detected":[43],"turns.":[45,67],"Compared":[46],"conventional":[48],"clustering-based":[49],"systems,":[51],"our":[52,83],"largely":[54,96],"reduces":[55,97],"computational":[57],"cost":[58],"of":[59,65,77],"clustering":[60],"due":[61],"sparsity":[64],"Unlike":[68],"other":[69],"supervised":[70],"systems":[73],"which":[74,95],"require":[75],"annotations":[76],"time-stamped":[78],"labels":[80],"training,":[82],"only":[85],"requires":[86],"including":[87],"tokens":[90],"during":[91],"transcribing":[93],"process,":[94],"human":[99],"efforts":[100],"involved":[101],"in":[102],"data":[103],"collection.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}