{"id":"https://openalex.org/W4391021454","doi":"https://doi.org/10.1109/asru57964.2023.10389679","title":"Transformer Attractors for Robust and Efficient End-To-End Neural Diarization","display_name":"Transformer Attractors for Robust and Efficient End-To-End Neural Diarization","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021454","doi":"https://doi.org/10.1109/asru57964.2023.10389679"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5004424826","display_name":"Lahiru Samarakoon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090344","display_name":"Fano Labs (China)","ror":"https://ror.org/008jsgk36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210090344"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lahiru Samarakoon","raw_affiliation_strings":["Fano Labs,Hong Kong","Fano Labs, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Fano Labs,Hong Kong","institution_ids":["https://openalex.org/I4210090344"]},{"raw_affiliation_string":"Fano Labs, Hong Kong","institution_ids":["https://openalex.org/I4210090344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004564614","display_name":"Samuel J. Broughton","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090344","display_name":"Fano Labs (China)","ror":"https://ror.org/008jsgk36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210090344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Samuel J Broughton","raw_affiliation_strings":["Fano Labs,Hong Kong","Fano Labs, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Fano Labs,Hong Kong","institution_ids":["https://openalex.org/I4210090344"]},{"raw_affiliation_string":"Fano Labs, Hong Kong","institution_ids":["https://openalex.org/I4210090344"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038038818","display_name":"Marc H\u00e4rk\u00f6nen","orcid":"https://orcid.org/0000-0002-0798-620X"},"institutions":[{"id":"https://openalex.org/I4210090344","display_name":"Fano Labs (China)","ror":"https://ror.org/008jsgk36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210090344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Marc H\u00e4rk\u00f6nen","raw_affiliation_strings":["Fano Labs,Hong Kong","Fano Labs, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Fano Labs,Hong Kong","institution_ids":["https://openalex.org/I4210090344"]},{"raw_affiliation_string":"Fano Labs, Hong Kong","institution_ids":["https://openalex.org/I4210090344"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042559717","display_name":"Ivan W. H. Fung","orcid":"https://orcid.org/0000-0002-4396-151X"},"institutions":[{"id":"https://openalex.org/I4210090344","display_name":"Fano Labs (China)","ror":"https://ror.org/008jsgk36","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210090344"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ivan Fung","raw_affiliation_strings":["Fano Labs,Hong Kong","Fano Labs, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Fano Labs,Hong Kong","institution_ids":["https://openalex.org/I4210090344"]},{"raw_affiliation_string":"Fano Labs, Hong Kong","institution_ids":["https://openalex.org/I4210090344"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5004424826"],"corresponding_institution_ids":["https://openalex.org/I4210090344"],"apc_list":null,"apc_paid":null,"fwci":1.1937,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.8383036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10320","display_name":"Neural Networks and Applications","score":0.9987000226974487,"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":0.9983000159263611,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7650203704833984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578918099403381},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.535485565662384},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3953106105327606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3917631208896637},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1348649263381958},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13285914063453674}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7650203704833984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578918099403381},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.535485565662384},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3953106105327606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3917631208896637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1348649263381958},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13285914063453674},{"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/asru57964.2023.10389679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2081074144","https://openalex.org/W2105482032","https://openalex.org/W2125336414","https://openalex.org/W2239847623","https://openalex.org/W2460742184","https://openalex.org/W2514740276","https://openalex.org/W2896457183","https://openalex.org/W2912083425","https://openalex.org/W2972949456","https://openalex.org/W3008357631","https://openalex.org/W3038871978","https://openalex.org/W3097777922","https://openalex.org/W3125118953","https://openalex.org/W3128434617","https://openalex.org/W3128688470","https://openalex.org/W3169291081","https://openalex.org/W3196595845","https://openalex.org/W3196857193","https://openalex.org/W3197189615","https://openalex.org/W3206479921","https://openalex.org/W3207834622","https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4225661121","https://openalex.org/W4288089799","https://openalex.org/W4296069292","https://openalex.org/W4297788887","https://openalex.org/W4297841547","https://openalex.org/W4319862481","https://openalex.org/W4372349651","https://openalex.org/W4385822541","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6769627184","https://openalex.org/W6779429391","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6790297703","https://openalex.org/W6796289742","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2938107654"],"abstract_inverted_index":{"End-to-end":[0],"neural":[1,17],"diarization":[2,13,22],"with":[3,53],"encoder-decoder":[4,33],"based":[5],"attractors":[6,40],"(EEND-EDA)":[7],"is":[8,61,78,125],"a":[9,15,24,36,54,64,68,91],"method":[10],"to":[11,50,79],"perform":[12],"in":[14,41],"single":[16],"network.":[18],"EDA":[19,52],"handles":[20],"the":[21,75,103,106],"of":[23,27,38,63,74,94,131],"flexible":[25],"number":[26],"speakers":[28],"by":[29,85],"using":[30],"an":[31,42],"LSTM-based":[32],"that":[34,114,130],"generates":[35],"set":[37,93],"speaker-wise":[39],"autoregressive":[43],"manner.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"replace":[51],"transformer-based":[55],"attractor":[56],"calculation":[57],"(TA)":[58],"module.":[59],"TA":[60],"composed":[62],"Combiner":[65],"block":[66,77],"and":[67],"Transformer":[69],"decoder.":[70,108],"The":[71],"main":[72],"function":[73],"combiner":[76],"generate":[80],"conversational":[81,88],"dependent":[82],"(CD)":[83],"embeddings":[84,98],"incorporating":[86],"learned":[87],"information":[89],"into":[90],"global":[92],"embeddings.":[95],"These":[96],"CD":[97],"will":[99],"then":[100],"serve":[101],"as":[102],"input":[104],"for":[105],"transformer":[107],"Results":[109],"on":[110],"public":[111],"datasets":[112],"show":[113],"EEND-TA":[115,123],"achieves":[116],"2.68%":[117],"absolute":[118],"DER":[119],"improvement":[120],"over":[121],"EEND-EDA.":[122,132],"inference":[124],"1.28":[126],"times":[127],"faster":[128],"than":[129]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}