{"id":"https://openalex.org/W4402112082","doi":"https://doi.org/10.21437/interspeech.2024-1062","title":"Unified Multi-Talker ASR with and without Target-speaker Enrollment","display_name":"Unified Multi-Talker ASR with and without Target-speaker Enrollment","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112082","doi":"https://doi.org/10.21437/interspeech.2024-1062"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1062","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1062","pdf_url":null,"source":null,"license":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082466886","display_name":"Naoki Makishima","orcid":"https://orcid.org/0000-0002-7065-315X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naoki Makishima","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101463708","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0002-9741-5573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027118468","display_name":"Mana Ihori","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mana Ihori","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016817412","display_name":"Naotaka Kawata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naotaka Kawata","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013009514","display_name":"Shota Orihashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shota Orihashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078963513","display_name":"Kazutoshi Shinoda","orcid":"https://orcid.org/0000-0003-1941-6172"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazutoshi Shinoda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102511251","display_name":"Taiga Yamane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taiga Yamane","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109312183","display_name":"Saki Mizuno","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saki Mizuno","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103222069","display_name":"Keita Suzuki","orcid":"https://orcid.org/0009-0006-7963-3952"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keita Suzuki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027868267","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0001-5343-4660"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079710814","display_name":"Nobukatsu Hojo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobukatsu Hojo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090978027","display_name":"Atsushi Ando","orcid":"https://orcid.org/0000-0002-0389-5001"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsushi Ando","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5060644399"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0336,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80652515,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"727","last_page":"731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9563000202178955,"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":0.9563000202178955,"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/T10575","display_name":"Wireless Communication Networks Research","score":0.932200014591217,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9004999995231628,"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/computer-science","display_name":"Computer science","score":0.6959954500198364},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.513494074344635},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.45983144640922546},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3454398810863495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6959954500198364},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.513494074344635},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.45983144640922546},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3454398810863495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1062","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1062","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W1521299571","https://openalex.org/W3162054169","https://openalex.org/W1516392727","https://openalex.org/W2140022733"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}