{"id":"https://openalex.org/W4415432684","doi":"https://doi.org/10.21437/interspeech.2025-2572","title":"Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition","display_name":"Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432684","doi":"https://doi.org/10.21437/interspeech.2025-2572"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-2572","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5120093695","display_name":"Asahi Sakuma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asahi Sakuma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025519045","display_name":"Hiroaki Sato","orcid":"https://orcid.org/0000-0002-2176-0215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroaki Sato","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093696","display_name":"Ryuga Sugano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryuga Sugano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006683103","display_name":"Tadashi Kumano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tadashi Kumano","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103084561","display_name":"Yoshihiko Kawai","orcid":"https://orcid.org/0000-0002-0811-9095"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshihiko Kawai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89106053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5503","last_page":"5507"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9868000149726868,"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":0.9868000149726868,"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/speaker-recognition","display_name":"Speaker recognition","score":0.4810999929904938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.32350000739097595},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.2678999900817871},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26170000433921814}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5961999893188477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5151000022888184},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35010001063346863},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27559998631477356},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.2409999966621399}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-2572","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-2572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}