{"id":"https://openalex.org/W4415433212","doi":"https://doi.org/10.21437/interspeech.2025-1595","title":"Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs","display_name":"Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433212","doi":"https://doi.org/10.21437/interspeech.2025-1595"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1595","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1595","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/A5034216052","display_name":"Hayato Futami","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hayato Futami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109644502","display_name":"Yosuke Kashiwagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Kashiwagi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036439738","display_name":"Yuki Ito","orcid":"https://orcid.org/0000-0003-1617-1595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Ito","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026215663","display_name":"Hassan Shahmohammadi","orcid":"https://orcid.org/0000-0002-3112-3252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hassan Shahmohammadi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047892839","display_name":"Siddhant Arora","orcid":"https://orcid.org/0000-0003-0375-496X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siddhant Arora","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5034216052"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7855,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9272711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9909999966621399,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9909999966621399,"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/training","display_name":"Training (meteorology)","score":0.6284999847412109},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.41339999437332153},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25690001249313354},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.22010000050067902}],"concepts":[{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5568000078201294},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4268999993801117},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.41339999437332153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22450000047683716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.22010000050067902}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-1595","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1595","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":2026,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-24T00:00:00"}
