{"id":"https://openalex.org/W4296070387","doi":"https://doi.org/10.21437/interspeech.2022-11032","title":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","display_name":"Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070387","doi":"https://doi.org/10.21437/interspeech.2022-11032"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11032","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11032","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5059951425","display_name":"Sravya Popuri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sravya Popuri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072019513","display_name":"Peng\u2010Jen Chen","orcid":"https://orcid.org/0000-0001-5400-905X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng-Jen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Changhan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Pino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005191803","display_name":"Yossi Adi","orcid":"https://orcid.org/0000-0003-2237-3898"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yossi Adi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112542984","display_name":"Jiatao Gu","orcid":"https://orcid.org/0000-0003-3578-2711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiatao Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084509956","display_name":"Ann Lee","orcid":"https://orcid.org/0000-0003-4300-9032"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ann Lee","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":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5195","last_page":"5199"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9714000225067139,"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":0.9714000225067139,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9498000144958496,"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/computer-science","display_name":"Computer science","score":0.77540522813797},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7184105515480042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6790529489517212},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.549419641494751},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5358039140701294},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5130914449691772},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4899401068687439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4657040238380432},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.44370681047439575},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.38331031799316406}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.77540522813797},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7184105515480042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6790529489517212},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.549419641494751},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5358039140701294},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5130914449691772},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4899401068687439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4657040238380432},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.44370681047439575},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.38331031799316406},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11032","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11032","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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":["https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W2338806053","https://openalex.org/W4385571610","https://openalex.org/W2972060578","https://openalex.org/W4285877427","https://openalex.org/W39235475","https://openalex.org/W783305165","https://openalex.org/W2990352702","https://openalex.org/W1540615732"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
