{"id":"https://openalex.org/W4402112428","doi":"https://doi.org/10.21437/interspeech.2024-616","title":"Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation","display_name":"Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112428","doi":"https://doi.org/10.21437/interspeech.2024-616"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-616","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-616","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/A5099173854","display_name":"Nameer Hirschkind","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nameer Hirschkind","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100321671","display_name":"Xiao Yu","orcid":"https://orcid.org/0000-0002-0314-9295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081255157","display_name":"Mahesh Kumar Nandwana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahesh Kumar Nandwana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101559537","display_name":"Joseph Liu","orcid":"https://orcid.org/0009-0006-7994-7716"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102690062","display_name":"Eloi DuBois","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eloi DuBois","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099173856","display_name":"Dao Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dao Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099173857","display_name":"Nicolas Thiebaut","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Thiebaut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104330008","display_name":"Colin Sinclair","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Colin Sinclair","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104330009","display_name":"Kyle Spence","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyle Spence","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101835397","display_name":"Charles Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charles Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056835997","display_name":"Zo\u00eb Abrams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoe Abrams","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101915673","display_name":"Morgan McGuire","orcid":"https://orcid.org/0000-0002-1759-6299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morgan McGuire","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5099173854"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11893399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"837","last_page":"841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9901999831199646,"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":0.9901999831199646,"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":0.9646999835968018,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9384999871253967,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-translation","display_name":"Speech translation","score":0.7485305666923523},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7155505418777466},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6018831133842468},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6004334092140198},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.588502824306488},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5132396221160889},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4122891426086426},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.3418937921524048},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.27129918336868286},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06389346718788147}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7485305666923523},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7155505418777466},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6018831133842468},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6004334092140198},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.588502824306488},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5132396221160889},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4122891426086426},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3418937921524048},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27129918336868286},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06389346718788147},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-616","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2024-616","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":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2293738010","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W4360995948","https://openalex.org/W1909292483"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
