{"id":"https://openalex.org/W4408355863","doi":"https://doi.org/10.1109/icassp49660.2025.10889446","title":"Mamba-based Segmentation Model for Speaker Diarization","display_name":"Mamba-based Segmentation Model for Speaker Diarization","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355863","doi":"https://doi.org/10.1109/icassp49660.2025.10889446"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05006565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092639568","display_name":"Alexis Plaquet","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Alexis Plaquet","raw_affiliation_strings":["NTT Corporation,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073111123","display_name":"Naohiro Tawara","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naohiro Tawara","raw_affiliation_strings":["NTT Corporation,Japan","NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan","NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026324656","display_name":"Shota Horiguchi","orcid":"https://orcid.org/0000-0002-3166-4956"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Horiguchi","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation (Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation (Japan)","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090978027","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-0389-5001"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":["NTT Corporation,Japan","NTT Human Informatics Laboratories (Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Human Informatics Laboratories (Japan)","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Corporation,Japan","NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":8.3651,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.97442797,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9876999855041504,"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":0.9876999855041504,"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":0.9272000193595886,"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":0.8591741323471069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261740565299988},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.578727662563324},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5130516290664673},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4852299690246582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36689916253089905}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8591741323471069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261740565299988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.578727662563324},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5130516290664673},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4852299690246582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36689916253089905}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889446","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05006565v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05006565","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2025, Hyderabab, India. pp.1-5, ⟨10.1109/ICASSP49660.2025.10889446⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05006565v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05006565","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2025, Hyderabab, India. pp.1-5, ⟨10.1109/ICASSP49660.2025.10889446⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2949676527","https://openalex.org/W2972949456","https://openalex.org/W2981087920","https://openalex.org/W3008357631","https://openalex.org/W3038871978","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3196117288","https://openalex.org/W3196595845","https://openalex.org/W3207834622","https://openalex.org/W3209984917","https://openalex.org/W4224939064","https://openalex.org/W4296069335","https://openalex.org/W4297841547","https://openalex.org/W4372340947","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823306","https://openalex.org/W4391892525","https://openalex.org/W4400615784","https://openalex.org/W4402111418","https://openalex.org/W4402111631","https://openalex.org/W4402111989","https://openalex.org/W4402112099","https://openalex.org/W4403511013","https://openalex.org/W4406461620","https://openalex.org/W4408354310","https://openalex.org/W4410087476","https://openalex.org/W6688816777","https://openalex.org/W6757817989","https://openalex.org/W6859298233","https://openalex.org/W6861387779","https://openalex.org/W6863679278","https://openalex.org/W6868789466","https://openalex.org/W7033105191"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Mamba":[0,51,94],"is":[1],"a":[2,9,97],"newly":[3],"proposed":[4,66,110],"architecture":[5],"that":[6],"behaves":[7],"like":[8],"recurrent":[10],"neural":[11,58],"network":[12],"(RNN)":[13],"with":[14,64],"attention-like":[15],"capabilities.":[16],"These":[17],"properties":[18],"are":[19,38],"promising":[20],"for":[21,31,52],"speaker":[22,87],"diarization,":[23],"as":[24],"attention-based":[25,107],"models":[26],"have":[27],"unsuitable":[28],"memory":[29],"requirements":[30],"long-form":[32],"audio,":[33],"and":[34,104],"traditional":[35,102],"RNN":[36,103],"capabilities":[37,72],"too":[39],"limited.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44],"propose":[45],"to":[46,95,100],"assess":[47],"the":[48,56,61,86,105],"potential":[49],"of":[50,60,75],"diarization":[53,82,120],"by":[54,84],"comparing":[55],"state-of-the-art":[57,114],"segmentation":[59],"pyannote":[62],"pipeline":[63],"our":[65],"Mamba-based":[67,111],"variant.":[68],"Mamba\u2019s":[69],"stronger":[70],"processing":[71],"allow":[73],"usage":[74],"longer":[76],"local":[77],"windows,":[78],"which":[79],"significantly":[80],"improve":[81],"quality":[83],"making":[85],"embedding":[88],"extraction":[89],"more":[90],"reliable.":[91],"We":[92],"find":[93],"be":[96],"superior":[98],"alternative":[99],"both":[101],"tested":[106],"model.":[108],"Our":[109],"system":[112],"achieves":[113],"performance":[115],"on":[116],"three":[117],"widely":[118],"used":[119],"datasets.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}