{"id":"https://openalex.org/W4297399268","doi":"https://doi.org/10.48550/arxiv.2204.05409","title":"Unified Speech-Text Pre-training for Speech Translation and Recognition","display_name":"Unified Speech-Text Pre-training for Speech Translation and Recognition","publication_year":2022,"publication_date":"2022-04-11","ids":{"openalex":"https://openalex.org/W4297399268","doi":"https://doi.org/10.48550/arxiv.2204.05409"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2204.05409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.05409","pdf_url":"https://arxiv.org/pdf/2204.05409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2204.05409","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052049405","display_name":"Yun Tang","orcid":"https://orcid.org/0000-0003-2340-1109","observed_orcids":["https://orcid.org/0000-0003-2340-1109"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Gong, Hongyu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Hongyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Dong, Ning","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Ning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087491225","display_name":"Changhan Wang","orcid":"https://orcid.org/0000-0002-1764-7105","observed_orcids":["https://orcid.org/0000-0002-1764-7105"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Changhan","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","observed_orcids":["https://orcid.org/0000-0001-5546-5217"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsu, Wei-Ning","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","observed_orcids":["https://orcid.org/0000-0003-3578-2711"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Jiatao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baevski, Alexei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100425999","display_name":"Xian Li","orcid":"https://orcid.org/0000-0001-5714-3940","observed_orcids":["https://orcid.org/0000-0001-5714-3940","https://orcid.org/0000-0003-3304-6702"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101170706","display_name":"Abdelrahman Mohamed","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed, Abdelrahman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459","observed_orcids":["https://orcid.org/0000-0001-5974-4459"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Auli, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058915697","display_name":"Juan Pino","orcid":"https://orcid.org/0009-0002-4895-7736","observed_orcids":["https://orcid.org/0009-0002-4895-7736"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pino, Juan","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":true,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0012000000569969416,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.00039999998989515007,"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/speech-translation","display_name":"speech translation","score":0.8240000009536743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.9869999885559082},{"id":"https://openalex.org/keywords/cross-modal-learning","display_name":"cross-modal learning","score":0.7289999723434448},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8790000081062317},{"id":"https://openalex.org/keywords/encoder-decoder-architecture","display_name":"encoder-decoder architecture","score":0.7160000205039978},{"id":"https://openalex.org/keywords/must-c","display_name":"MuST-C","score":0.8209999799728394},{"id":"https://openalex.org/keywords/librispeech","display_name":"LibriSpeech","score":0.9879999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8031780123710632},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7212417125701904},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.6382983922958374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189315915107727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6122324466705322},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5646600127220154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5046783685684204},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4877477288246155},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.41913890838623047},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.38456517457962036},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.35310640931129456},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2204.05409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.05409","pdf_url":"https://arxiv.org/pdf/2204.05409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2204.05409","doi":"https://doi.org/10.48550/arxiv.2204.05409","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2204.05409","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2204.05409","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2204.05409","pdf_url":"https://arxiv.org/pdf/2204.05409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297399268.pdf","grobid_xml":"https://content.openalex.org/works/W4297399268.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3207222250","https://openalex.org/W4392979802","https://openalex.org/W4385573012","https://openalex.org/W4308349017","https://openalex.org/W4221155340","https://openalex.org/W4372260307","https://openalex.org/W4382318914","https://openalex.org/W3126261584","https://openalex.org/W4310271076","https://openalex.org/W4408353156"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,42],"method":[3,22,111],"to":[4,45,62,102,145],"jointly":[5],"pre-train":[6],"speech":[7,16,35,39,58,64,82,95,115,139,151],"and":[8,18,26,41,65,97,116,126,142],"text":[9,44,46,52,66,78,117],"in":[10,72],"an":[11],"encoder-decoder":[12],"modeling":[13,67],"framework":[14],"for":[15,29,94],"translation":[17,96,140],"recognition.":[19],"The":[20],"proposed":[21,110],"incorporates":[23],"four":[24],"self-supervised":[25,34],"supervised":[27,57],"subtasks":[28],"cross":[30],"modality":[31],"learning.":[32],"A":[33],"subtask":[36,47,104],"leverages":[37],"unlabelled":[38],"data,":[40],"(self-)supervised":[43],"makes":[48],"use":[49],"of":[50,133],"abundant":[51],"training":[53],"data.":[54],"Two":[55,91],"auxiliary":[56],"tasks":[59],"are":[60,100],"included":[61],"unify":[63],"space.":[68],"Our":[69,106],"contribution":[70],"lies":[71],"integrating":[73],"linguistic":[74],"information":[75,118],"from":[76],"the":[77,81,109,131,134,137,149],"corpus":[79],"into":[80,119],"pre-training.":[83],"Detailed":[84],"analysis":[85],"reveals":[86],"learning":[87],"interference":[88],"among":[89],"subtasks.":[90],"pre-training":[92],"configurations":[93],"recognition,":[98],"respectively,":[99],"presented":[101],"alleviate":[103],"interference.":[105],"experiments":[107],"show":[108],"can":[112],"effectively":[113],"fuse":[114],"one":[120],"model.":[121],"It":[122],"achieves":[123],"between":[124],"1.7":[125],"2.3":[127],"BLEU":[128],"improvement":[129],"above":[130],"state":[132],"art":[135],"on":[136,148],"MuST-C":[138],"dataset":[141],"comparable":[143],"WERs":[144],"wav2vec":[146],"2.0":[147],"Librispeech":[150],"recognition":[152],"task.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-09-28T00:00:00"}