{"id":"https://openalex.org/W4415433511","doi":"https://doi.org/10.21437/interspeech.2025-874","title":"Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","display_name":"Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433511","doi":"https://doi.org/10.21437/interspeech.2025-874"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-874","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-874","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":"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/A5029338576","display_name":"Ke Hu","orcid":"https://orcid.org/0000-0002-1599-1519"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020404017","display_name":"Ehsan Hosseini-Asl","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsan Hosseini-Asl","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418547","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-1957-6432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025318789","display_name":"Edresson Casanova","orcid":"https://orcid.org/0000-0003-0160-7173"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edresson Casanova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935896","display_name":"Subhankar Ghosh","orcid":"https://orcid.org/0000-0001-9191-5684"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhankar Ghosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr \u017belasko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762970","display_name":"Jason Li","orcid":"https://orcid.org/0000-0002-1150-3549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040747392","display_name":"Jagadeesh Balam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jagadeesh Balam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2715","last_page":"2719"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9660000205039978,"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":0.9660000205039978,"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":0.9574000239372253,"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/language-model","display_name":"Language model","score":0.4350000023841858},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3384000062942505},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.3224000036716461},{"id":"https://openalex.org/keywords/modeling-language","display_name":"Modeling language","score":0.29980000853538513},{"id":"https://openalex.org/keywords/duplex","display_name":"Duplex (building)","score":0.25839999318122864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6317999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4350000023841858},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3765999972820282},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3521000146865845},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C99611785","wikidata":"https://www.wikidata.org/wiki/Q6453233","display_name":"Duplex (building)","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-874","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-874","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-24T00:00:00"}
