{"id":"https://openalex.org/W4408356036","doi":"https://doi.org/10.1109/icassp49660.2025.10887711","title":"Guided Speaker Embedding","display_name":"Guided Speaker Embedding","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356036","doi":"https://doi.org/10.1109/icassp49660.2025.10887711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887711","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":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/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/A5061074419","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-3971-0654"},"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/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/A5101739550","display_name":"Hiroshi Sato","orcid":"https://orcid.org/0000-0001-6575-0396"},"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9890000224113464,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9890000224113464,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9819999933242798,"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":0.7017653584480286},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5541474223136902},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5216520428657532},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2046070396900177}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7017653584480286},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5541474223136902},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5216520428657532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2046070396900177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887711","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887711","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2083751884","https://openalex.org/W2194775991","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2890964092","https://openalex.org/W2900212944","https://openalex.org/W2981087920","https://openalex.org/W3007946293","https://openalex.org/W3015783745","https://openalex.org/W3020336359","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3094374485","https://openalex.org/W3097206043","https://openalex.org/W3109079702","https://openalex.org/W3142516134","https://openalex.org/W3161590371","https://openalex.org/W3163903701","https://openalex.org/W3186652349","https://openalex.org/W3196117288","https://openalex.org/W3196595845","https://openalex.org/W3196857193","https://openalex.org/W3207834622","https://openalex.org/W4221147513","https://openalex.org/W4224920409","https://openalex.org/W4226098957","https://openalex.org/W4226491018","https://openalex.org/W4296069335","https://openalex.org/W4362683557","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823344","https://openalex.org/W4392904030","https://openalex.org/W4392904174","https://openalex.org/W4395471098","https://openalex.org/W4406461483","https://openalex.org/W4408353520","https://openalex.org/W6688816777"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"guided":[4],"speaker":[5,11,16,44,56,78,98,153,167,170],"embedding":[6,57,105],"extraction":[7,58],"system,":[8],"which":[9,150],"extracts":[10],"embeddings":[12,47,68,79],"of":[13,20,106,118,146,160],"the":[14,52,67,104,107,116,130,135,143,147,151,161],"target":[15,21,119,152],"using":[17,97],"speech":[18,70],"activities":[19,99],"and":[22,41,120,169],"interference":[23,72],"speakers":[24,122],"as":[25,100],"clues.":[26],"Several":[27],"methods":[28],"for":[29,51,139],"long-form":[30],"overlapped":[31],"multi-speaker":[32],"audio":[33],"processing":[34,40],"are":[35,48,88,156],"typically":[36],"two-staged:":[37],"i)":[38],"segment-level":[39],"ii)":[42],"inter-segment":[43],"matching.":[45],"Speaker":[46],"often":[49,76],"used":[50,138],"latter":[53],"purpose.":[54],"Typical":[55],"approaches":[59],"only":[60],"use":[61],"single-speaker":[62],"intervals":[63,87,148],"to":[64,81,102,123,129],"avoid":[65],"corrupting":[66],"with":[69],"from":[71,110],"speakers.":[73],"However,":[74],"this":[75,93],"makes":[77],"impossible":[80],"extract":[82,103],"because":[83],"sufficiently":[84],"long":[85],"non-overlapping":[86],"not":[89],"always":[90],"available.":[91],"In":[92],"paper,":[94],"we":[95,114],"propose":[96],"clues":[101],"speaker-of-interest":[108],"directly":[109],"overlapping":[111],"speech.":[112],"Specifically,":[113],"concatenate":[115],"activity":[117],"non-target":[121],"acoustic":[124],"features":[125],"before":[126],"being":[127],"fed":[128],"model.":[131],"We":[132],"also":[133],"condition":[134],"attention":[136,144],"weights":[137,145],"pooling":[140],"so":[141],"that":[142],"in":[149,166],"is":[154,164],"inactive":[155],"zero.":[157],"The":[158],"effectiveness":[159],"proposed":[162],"method":[163],"demonstrated":[165],"verification":[168],"diarization.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}