{"id":"https://openalex.org/W4402111989","doi":"https://doi.org/10.21437/interspeech.2024-668","title":"EEND-M2F: Masked-attention mask transformers for speaker diarization","display_name":"EEND-M2F: Masked-attention mask transformers for speaker diarization","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402111989","doi":"https://doi.org/10.21437/interspeech.2024-668"},"language":"nl","primary_location":{"id":"doi:10.21437/interspeech.2024-668","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-668","pdf_url":"https://www.isca-archive.org/interspeech_2024/harkonen24_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/harkonen24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038038818","display_name":"Marc H\u00e4rk\u00f6nen","orcid":"https://orcid.org/0000-0002-0798-620X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Marc H\u00e4rk\u00f6nen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004564614","display_name":"Samuel J. Broughton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel J. Broughton","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004424826","display_name":"Lahiru Samarakoon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lahiru Samarakoon","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038038818"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.6372,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.96463105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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":0.9945999979972839,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9628999829292297,"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/T12031","display_name":"Speech and dialogue systems","score":0.9628999829292297,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.618395209312439},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.593791663646698},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5622936487197876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48960310220718384},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3510463833808899},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12887611985206604},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12574830651283264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.618395209312439},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.593791663646698},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5622936487197876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48960310220718384},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3510463833808899},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12887611985206604},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12574830651283264},{"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:10.21437/interspeech.2024-668","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-668","pdf_url":"https://www.isca-archive.org/interspeech_2024/harkonen24_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-668","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-668","pdf_url":"https://www.isca-archive.org/interspeech_2024/harkonen24_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402111989.pdf","grobid_xml":"https://content.openalex.org/works/W4402111989.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,18],"make":[4],"the":[5,29,51,65,96,101],"explicit":[6],"connection":[7],"between":[8],"image":[9],"segmentation":[10,69],"methods":[11],"and":[12,61,86],"end-to-end":[13,23],"diarization":[14,24],"methods.From":[15],"these":[16],"insights,":[17],"propose":[19],"a":[20,38],"novel,":[21],"fully":[22],"model,":[25],"EEND-M2F,":[26],"based":[27],"on":[28,78,93],"Mask2Former":[30],"architecture.Speaker":[31],"representations":[32],"are":[33,47],"computed":[34],"in":[35,43],"parallel":[36],"using":[37,54],"stack":[39],"of":[40,91],"transformer":[41],"decoders,":[42],"which":[44],"irrelevant":[45],"frames":[46],"explicitly":[48],"masked":[49],"from":[50,56],"cross":[52],"attention":[53],"predictions":[55],"previous":[57],"layers.EEND-M2F":[58],"is":[59,95],"efficient,":[60],"truly":[62],"end-to-end,":[63],"eliminating":[64],"need":[66],"for":[67],"additional":[68],"models":[70],"or":[71],"clustering":[72],"algorithms.Our":[73],"model":[74],"achieves":[75],"state-of-the-art":[76],"performance":[77],"several":[79],"public":[80],"datasets,":[81],"such":[82],"as":[83],"AMI,":[84],"AliMeeting":[85],"RAMC.Most":[87],"notably":[88],"our":[89],"DER":[90],"16.07%":[92],"DIHARD-III":[94],"first":[97],"major":[98],"improvement":[99],"upon":[100],"challenge":[102],"winning":[103],"system.":[104]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}