{"id":"https://openalex.org/W3158287709","doi":"https://doi.org/10.1109/icassp39728.2021.9414841","title":"End-To-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings","display_name":"End-To-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3158287709","doi":"https://doi.org/10.1109/icassp39728.2021.9414841","mag":"3158287709"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.02096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"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":true,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"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":"Hakan Erdogan","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"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":"Kevin Wilson","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"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":"Scott Wisdom","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","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":"John R. Hershey","raw_affiliation_strings":["Google Research","Google Research,"],"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Research,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010858961"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05335044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7183","last_page":"7187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9141336679458618},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8005245327949524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7413359880447388},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6543641090393066},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5470262169837952},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5006616115570068},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4148576557636261},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4055710434913635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3956175148487091},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.330069363117218}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9141336679458618},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8005245327949524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7413359880447388},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6543641090393066},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5470262169837952},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5006616115570068},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4148576557636261},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4055710434913635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3956175148487091},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.330069363117218},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.02096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.02096","pdf_url":"https://arxiv.org/pdf/2105.02096","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2105.02096","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.02096","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/q3gc-9v97","is_oa":true,"landing_page_url":"https://doi.org/10.17023/q3gc-9v97","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3158287709","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.02096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.02096","pdf_url":"https://arxiv.org/pdf/2105.02096","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158287709.pdf","grobid_xml":"https://content.openalex.org/works/W3158287709.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1485783873","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2081074144","https://openalex.org/W2150769028","https://openalex.org/W2159591770","https://openalex.org/W2176412452","https://openalex.org/W2521624909","https://openalex.org/W2638067502","https://openalex.org/W2896538040","https://openalex.org/W2938358845","https://openalex.org/W2952218014","https://openalex.org/W2952752702","https://openalex.org/W2962788625","https://openalex.org/W2963403868","https://openalex.org/W2963470929","https://openalex.org/W2972449503","https://openalex.org/W2972949456","https://openalex.org/W2973127116","https://openalex.org/W2981608174","https://openalex.org/W2985913104","https://openalex.org/W2992261503","https://openalex.org/W3008357631","https://openalex.org/W3010196324","https://openalex.org/W3016031604","https://openalex.org/W3016232124","https://openalex.org/W3024085360","https://openalex.org/W3025260599","https://openalex.org/W3026868282","https://openalex.org/W3033627755","https://openalex.org/W3037798801","https://openalex.org/W3095212884","https://openalex.org/W6674036243","https://openalex.org/W6682600690","https://openalex.org/W6685562342","https://openalex.org/W6739901393","https://openalex.org/W6769530546","https://openalex.org/W6770434673","https://openalex.org/W6774558098","https://openalex.org/W6779069803","https://openalex.org/W6779709467"],"related_works":["https://openalex.org/W2972949456","https://openalex.org/W3043471679","https://openalex.org/W3095129427","https://openalex.org/W3008849579","https://openalex.org/W3144086690","https://openalex.org/W3015621653","https://openalex.org/W2578538565","https://openalex.org/W2748026385","https://openalex.org/W3093864324","https://openalex.org/W2405970501","https://openalex.org/W180663858","https://openalex.org/W2808772541","https://openalex.org/W3026868282","https://openalex.org/W2110783210","https://openalex.org/W2981473019","https://openalex.org/W2106780157","https://openalex.org/W2536165811","https://openalex.org/W3015778863","https://openalex.org/W202282565","https://openalex.org/W71947379"],"abstract_inverted_index":{"We":[0,57],"present":[1],"an":[2],"end-to-end":[3,141],"deep":[4],"network":[5,72],"model":[6,93,135],"that":[7,61],"performs":[8,136],"meeting":[9,107],"diarization":[10,16,35,66,142],"from":[11],"single-channel":[12],"audio":[13],"recordings.":[14],"End-to-end":[15],"models":[17,143],"have":[18],"the":[19,92],"advantage":[20],"of":[21,29,48,123],"handling":[22,28],"speaker":[23,84],"overlap":[24],"and":[25,87,103,112],"enabling":[26],"straightforward":[27],"discriminative":[30],"training,":[31],"unlike":[32],"traditional":[33],"clustering-based":[34],"methods.":[36],"The":[37,133],"proposed":[38,134,140],"system":[39],"is":[40,94],"designed":[41],"to":[42,63],"handle":[43],"meetings":[44,125],"with":[45,65,96],"unknown":[46],"numbers":[47],"speakers,":[49],"using":[50,82,119,127],"variable-number":[51],"permutation-invariant":[52],"cross-entropy":[53],"based":[54,109],"loss":[55],"functions.":[56],"introduce":[58],"several":[59],"components":[60],"appear":[62],"help":[64],"performance,":[67],"including":[68],"a":[69,75,83,88,97],"local":[70],"convolutional":[71],"followed":[73],"by":[74],"global":[76],"self-attention":[77],"module,":[78],"multitask":[79],"transfer":[80],"learning":[81],"identification":[85],"component,":[86],"sequential":[89],"approach":[90],"where":[91],"refined":[95],"second":[98],"stage.":[99],"These":[100],"are":[101,117],"trained":[102],"validated":[104],"on":[105,110,144],"simulated":[106,124],"data":[108],"LibriSpeech":[111],"LibriTTS":[113],"datasets;":[114],"final":[115],"evaluations":[116],"done":[118],"LibriCSS,":[120],"which":[121],"consists":[122],"recorded":[126],"real":[128],"acoustics":[129],"via":[130],"loudspeaker":[131],"playback.":[132],"better":[137],"than":[138],"previously":[139],"these":[145],"data.":[146]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}