{"id":"https://openalex.org/W4406461483","doi":"https://doi.org/10.1109/slt61566.2024.10832241","title":"Recursive Attentive Pooling For Extracting Speaker Embeddings From Multi-Speaker Recordings","display_name":"Recursive Attentive Pooling For Extracting Speaker Embeddings From Multi-Speaker Recordings","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461483","doi":"https://doi.org/10.1109/slt61566.2024.10832241"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/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"],"raw_orcid":null,"affiliations":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"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":"Takafumi Moriya","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/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"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":"Takanori Ashihara","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/A5059753087","display_name":"Hiroshi Sato","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":"Hiroshi Sato","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"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":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1201","last_page":"1208"},"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":0.9998000264167786,"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":0.9998000264167786,"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/pooling","display_name":"Pooling","score":0.8149678707122803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7998661398887634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7239672541618347},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6142936944961548},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6117697954177856},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.42083296179771423},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36312800645828247}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8149678707122803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7998661398887634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7239672541618347},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6142936944961548},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6117697954177856},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.42083296179771423},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36312800645828247}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W2083751884","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2221409856","https://openalex.org/W2606974598","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2794506738","https://openalex.org/W2889052710","https://openalex.org/W2890964092","https://openalex.org/W2891054259","https://openalex.org/W2891833136","https://openalex.org/W2946508582","https://openalex.org/W2962788625","https://openalex.org/W2963260202","https://openalex.org/W2964238697","https://openalex.org/W2972369255","https://openalex.org/W2972680151","https://openalex.org/W2973062255","https://openalex.org/W2981087920","https://openalex.org/W2997419692","https://openalex.org/W3008104819","https://openalex.org/W3008357631","https://openalex.org/W3013020904","https://openalex.org/W3015611708","https://openalex.org/W3015780472","https://openalex.org/W3016232124","https://openalex.org/W3024085360","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3095992690","https://openalex.org/W3096090308","https://openalex.org/W3097206043","https://openalex.org/W3105031100","https://openalex.org/W3142516134","https://openalex.org/W3147778289","https://openalex.org/W3162347631","https://openalex.org/W3163019736","https://openalex.org/W3163903701","https://openalex.org/W3166898278","https://openalex.org/W3195050710","https://openalex.org/W3196857193","https://openalex.org/W3212886388","https://openalex.org/W4220731890","https://openalex.org/W4221153233","https://openalex.org/W4224939064","https://openalex.org/W4226090390","https://openalex.org/W4297841362","https://openalex.org/W4297841877","https://openalex.org/W4319862221","https://openalex.org/W4362683557","https://openalex.org/W4367597591","https://openalex.org/W4372267289","https://openalex.org/W4372271885","https://openalex.org/W4385823344","https://openalex.org/W4392904351","https://openalex.org/W4402111799","https://openalex.org/W6631190155","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939","https://openalex.org/W2144470400","https://openalex.org/W1516392727","https://openalex.org/W2140022733","https://openalex.org/W2911612049"],"abstract_inverted_index":{"This":[0,126],"paper":[1],"proposes":[2],"a":[3,13,48,89],"method":[4,104,177],"for":[5,9,25,30,76,91,134],"extracting":[6,65,77],"speaker":[7,11,26,37,60,78,179],"embedding":[8,61],"each":[10,92],"from":[12,68,81,121],"variable-length":[14],"recording":[15],"containing":[16],"multiple":[17,109],"speakers.":[18,168],"Speaker":[19],"embeddings":[20,66,79,107,119],"are":[21],"crucial":[22],"not":[23],"only":[24,67],"recognition":[27],"but":[28,84],"also":[29],"various":[31,165],"multi-speaker":[32,55,82,124],"speech":[33,41,51],"applications":[34],"such":[35],"as":[36],"diarization":[38,182],"and":[39,181],"target-speaker":[40],"processing.":[42],"Despite":[43],"the":[44,106,117,122,136,143,149,154,158,172,175],"challenges":[45],"of":[46,95,108,116,151,167,174],"obtaining":[47],"single":[49],"speaker\u2019s":[50],"without":[52],"pre-registration":[53],"in":[54,153,178],"scenarios,":[56],"most":[57],"studies":[58],"on":[59,64,113],"extraction":[62],"focus":[63],"single-speaker":[69],"recordings.":[70],"Some":[71],"methods":[72],"have":[73],"been":[74],"proposed":[75,103,176],"directly":[80],"recordings,":[83],"they":[85],"typically":[86],"require":[87],"preparing":[88],"model":[90,160],"possible":[93],"number":[94,150],"speakers":[96,110,152],"or":[97],"involve":[98],"complicated":[99],"training":[100],"procedures.":[101],"The":[102],"computes":[105],"by":[111,129],"focusing":[112],"different":[114],"parts":[115],"frame-wise":[118,137],"extracted":[120],"input":[123],"audio.":[125],"is":[127],"achieved":[128],"recursively":[130],"computing":[131],"attention":[132,145],"weights":[133,146],"pooling":[135],"embeddings.":[138],"Additionally,":[139],"we":[140],"propose":[141],"using":[142],"calculated":[144],"to":[147,161,164],"estimate":[148],"recording,":[155],"which":[156],"allows":[157],"same":[159],"be":[162],"applied":[163],"numbers":[166],"Experimental":[169],"evaluations":[170],"demonstrate":[171],"effectiveness":[173],"verification":[180],"tasks.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}