{"id":"https://openalex.org/W4319862725","doi":"https://doi.org/10.1109/slt54892.2023.10023388","title":"Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization","display_name":"Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862725","doi":"https://doi.org/10.1109/slt54892.2023.10023388"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10023388","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023388","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/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087545401","display_name":"Yuki Takashima","orcid":"https://orcid.org/0000-0001-8489-9487"},"institutions":[{"id":"https://openalex.org/I65143321","display_name":"Hitachi (Japan)","ror":"https://ror.org/02exqgm79","country_code":"JP","type":"company","lineage":["https://openalex.org/I65143321"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Takashima","raw_affiliation_strings":["Hitachi, Ltd.,Japan","Hitachi, Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hitachi, Ltd.,Japan","institution_ids":["https://openalex.org/I65143321"]},{"raw_affiliation_string":"Hitachi, Ltd., Japan","institution_ids":["https://openalex.org/I65143321"]}]},{"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/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726"},"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":"Paola Garcia","raw_affiliation_strings":["Johns Hopkins University,USA","Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4356,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.54390749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"620","last_page":"625"},"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":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/channel","display_name":"Channel (broadcasting)","score":0.8066456317901611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.758901834487915},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7252605557441711},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6123526692390442},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.41749921441078186},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4051956534385681},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3456175923347473},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15844783186912537}],"concepts":[{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.8066456317901611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758901834487915},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7252605557441711},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6123526692390442},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.41749921441078186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4051956534385681},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3456175923347473},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15844783186912537}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10023388","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10023388","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2081074144","https://openalex.org/W2219249508","https://openalex.org/W2294370754","https://openalex.org/W2402040300","https://openalex.org/W2589857635","https://openalex.org/W2640112133","https://openalex.org/W2711861986","https://openalex.org/W2747909401","https://openalex.org/W2785745830","https://openalex.org/W2891984996","https://openalex.org/W2892025684","https://openalex.org/W2892163332","https://openalex.org/W2896538040","https://openalex.org/W2896555122","https://openalex.org/W2954695182","https://openalex.org/W2963458655","https://openalex.org/W2964038834","https://openalex.org/W2972992051","https://openalex.org/W3004309045","https://openalex.org/W3008008574","https://openalex.org/W3008762051","https://openalex.org/W3015372568","https://openalex.org/W3016232124","https://openalex.org/W3016244460","https://openalex.org/W3025260599","https://openalex.org/W3096073522","https://openalex.org/W3187295906","https://openalex.org/W3207360934","https://openalex.org/W3207570488","https://openalex.org/W4220731890","https://openalex.org/W4225632569","https://openalex.org/W4319586472","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6688816777","https://openalex.org/W6735168207","https://openalex.org/W6755174555","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W4225792560","https://openalex.org/W2312116756","https://openalex.org/W4287236246","https://openalex.org/W4287164729","https://openalex.org/W4308022734","https://openalex.org/W155763510","https://openalex.org/W2142742027","https://openalex.org/W3015923889","https://openalex.org/W4308164622","https://openalex.org/W4289029557"],"abstract_inverted_index":{"Due":[0],"to":[1,68,105,117],"the":[2,12,30,70,113,128],"high":[3],"performance":[4],"of":[5],"multi-channel":[6,16,42,48,90,103,119,135],"speech":[7,38,49],"processing,":[8],"we":[9,95],"can":[10,40,85],"use":[11],"outputs":[13],"from":[14,101,112],"a":[15,23,102,106,118],"model":[17,25,58,83,104,108,116],"as":[18],"teacher":[19],"labels":[20],"when":[21],"training":[22,52],"single-channel":[24,37,107,115],"with":[26,47],"knowledge":[27,73,99],"distillation.":[28],"To":[29],"contrary,":[31],"it":[32,46,56],"is":[33],"also":[34],"known":[35],"that":[36,84,127],"data":[39,50,125],"benefit":[41],"models":[43],"by":[44,54],"mixing":[45],"during":[51],"or":[53],"using":[55],"for":[57],"pretraining.":[59],"This":[60],"paper":[61],"focuses":[62],"on":[63,123],"speaker":[64,136],"diarization":[65,82,137],"and":[66,89,109,134],"proposes":[67],"conduct":[69,97],"above":[71],"bi-directional":[72],"transfer":[74],"alternately.":[75],"We":[76],"first":[77],"introduce":[78],"an":[79],"end-to-end":[80],"neural":[81],"handle":[86],"both":[87],"single-":[88,133],"inputs.":[91],"Using":[92],"this":[93],"model,":[94],"alternately":[96],"i)":[98],"distillation":[100],"ii)":[110],"finetuning":[111],"distilled":[114],"model.":[120],"Experimental":[121],"results":[122],"two-speaker":[124],"show":[126],"proposed":[129],"method":[130],"mutually":[131],"improved":[132],"performances.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}