{"id":"https://openalex.org/W4280601369","doi":"https://doi.org/10.21437/interspeech.2022-10011","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","display_name":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4280601369","doi":"https://doi.org/10.21437/interspeech.2022-10011"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10011","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10011","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":"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/A5100674914","display_name":"Qianqian Dong","orcid":"https://orcid.org/0009-0001-7001-7583"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qianqian Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069891577","display_name":"Fengpeng Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fengpeng Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043256966","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0000-0002-2858-6512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028733018","display_name":"Qibing Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qibing Bai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433533","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-3250-4284"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100674914"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1434,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79524887,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1781","last_page":"1785"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/T10028","display_name":"Topic Modeling","score":0.9866999983787537,"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":0.8076242208480835},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7732019424438477},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6311616897583008},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5832327604293823},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5492411255836487},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5296608805656433},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4349464178085327},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42849892377853394},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.40444818139076233}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076242208480835},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7732019424438477},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6311616897583008},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5832327604293823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5492411255836487},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5296608805656433},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4349464178085327},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42849892377853394},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.40444818139076233},{"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/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.2022-10011","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10011","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":{"grobid_xml":false,"pdf":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/W39235475","https://openalex.org/W1540615732","https://openalex.org/W3013209356","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971"],"abstract_inverted_index":{"Direct":[0],"Speech-to-speech":[1],"translation":[2],"(S2ST)":[3],"has":[4],"drawn":[5],"more":[6,8],"and":[7,20,54,96],"attention":[9],"recently.":[10],"The":[11],"task":[12],"is":[13,103],"very":[14],"challenging":[15],"due":[16],"to":[17,84],"data":[18,51,71],"scarcity":[19],"complex":[21],"speech-to-speech":[22],"mapping.":[23],"In":[24],"this":[25],"paper,":[26],"we":[27,35,47,67,87],"report":[28],"our":[29,89],"recent":[30],"achievements":[31],"in":[32],"S2ST.":[33,85],"Firstly,":[34],"build":[36],"a":[37,56,73],"S2ST":[38],"Transformer":[39],"baseline":[40],"which":[41,78],"outperforms":[42],"the":[43,49,61,69],"original":[44],"Translatotron.":[45],"Secondly,":[46],"utilize":[48],"external":[50],"by":[52],"pseudo-labeling":[53],"obtain":[55],"new":[57],"state-of-the-art":[58],"result":[59],"on":[60,91],"Fisher":[62],"English-to-Spanish":[63],"test":[64],"set.":[65],"Indeed,":[66],"exploit":[68],"pseudo":[70],"with":[72],"combination":[74],"of":[75],"popular":[76],"techniques":[77],"are":[79],"not":[80],"trivial":[81],"when":[82],"applied":[83],"Moreover,":[86],"evaluate":[88],"approach":[90],"both":[92],"syntactically":[93],"similar":[94],"(Spanish-English)":[95],"distant":[97],"(English-Chinese)":[98],"language":[99],"pairs.":[100],"Our":[101],"implementation":[102],"available":[104],"at":[105],"https://github.com/fengpeng-yue/speech-to-speech-translation.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}