{"id":"https://openalex.org/W3196833881","doi":"https://doi.org/10.21437/interspeech.2021-1065","title":"End-to-End Speech Translation via Cross-Modal Progressive Training","display_name":"End-to-End Speech Translation via Cross-Modal Progressive Training","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3196833881","doi":"https://doi.org/10.21437/interspeech.2021-1065","mag":"3196833881"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1065","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5100624648","display_name":"Rong Ye","orcid":"https://orcid.org/0000-0002-6693-3079"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong Ye","raw_affiliation_strings":["ByteDance AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101693713","display_name":"Mingxuan Wang","orcid":"https://orcid.org/0009-0008-3376-6762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingxuan Wang","raw_affiliation_strings":["ByteDance AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440407","display_name":"Lei Li","orcid":"https://orcid.org/0000-0003-3095-9776"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Li","raw_affiliation_strings":["ByteDance AI Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab, Shanghai, China","institution_ids":[]}]}],"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":46,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2267","last_page":"2271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9954000115394592,"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":0.9927999973297119,"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":0.6144726276397705},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5720075368881226},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5490720868110657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4905228018760681},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.48990386724472046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27578848600387573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144726276397705},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5720075368881226},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5490720868110657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4905228018760681},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.48990386724472046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27578848600387573},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-1065","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1065","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2419539795","https://openalex.org/W2512924740","https://openalex.org/W2785350307","https://openalex.org/W2949328740","https://openalex.org/W2962680099","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2964172053","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W2986963494","https://openalex.org/W3017454464","https://openalex.org/W3034571331","https://openalex.org/W3036601975","https://openalex.org/W3036839309","https://openalex.org/W3037217258","https://openalex.org/W3049256661","https://openalex.org/W3096490862","https://openalex.org/W3097787369","https://openalex.org/W3105669983","https://openalex.org/W3105825505","https://openalex.org/W3113594615","https://openalex.org/W3113676066","https://openalex.org/W3113908264","https://openalex.org/W3162037819","https://openalex.org/W3175809709","https://openalex.org/W4287329822","https://openalex.org/W4287374065","https://openalex.org/W4287629556","https://openalex.org/W4288817190","https://openalex.org/W4300558631","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2954695182","https://openalex.org/W4224917401","https://openalex.org/W4303519918","https://openalex.org/W2600628583","https://openalex.org/W2771275309"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,63],"translation":[2,39,73],"models":[3,20],"have":[4],"become":[5],"a":[6,83,91,102],"new":[7],"trend":[8],"in":[9],"research":[10],"due":[11],"to":[12,29,95],"their":[13],"potential":[14],"of":[15,26,109,134],"reducing":[16],"error":[17],"propagation.However,":[18],"these":[19],"still":[21,43],"suffer":[22],"from":[23,37,77],"the":[24,88,107,114,137],"challenge":[25],"data":[27],"scarcity.How":[28],"effectively":[30],"use":[31],"unlabeled":[32],"or":[33],"other":[34],"parallel":[35,98],"corpora":[36],"machine":[38],"is":[40],"promising":[41],"but":[42],"an":[44,55,131],"open":[45],"problem.In":[46],"this":[47],"paper,":[48],"we":[49],"propose":[50],"Cross":[51],"Speech-Text":[52],"Network":[53],"(XSTNet),":[54],"end-to-end":[56],"model":[57,75],"for":[58],"speech-to-text":[59],"translation.XSTNet":[60],"takes":[61],"both":[62,70],"and":[64,68,72,101,111,117,146],"text":[65],"as":[66,87],"input":[67],"outputs":[69],"transcription":[71],"text.The":[74],"benefits":[76],"its":[78],"three":[79],"key":[80],"design":[81],"aspects:":[82],"self-supervised":[84],"pretrained":[85],"sub-network":[86],"audio":[89],"encoder,":[90],"multi-task":[92],"training":[93,104],"objective":[94],"exploit":[96],"additional":[97],"bilingual":[99],"text,":[100],"progressive":[103],"procedure.We":[105],"evaluate":[106],"performance":[108],"XSTNet":[110,122],"baselines":[112],"on":[113,126],"MuST-C":[115],"En-X":[116],"LibriSpeech":[118],"En-Fr":[119],"datasets.In":[120],"particular,":[121],"achieves":[123],"state-of-the-art":[124],"results":[125],"all":[127],"language":[128],"directions":[129],"with":[130],"average":[132],"BLEU":[133],"28.8,":[135],"outperforming":[136],"previous":[138],"best":[139],"method":[140],"by":[141],"3.2":[142],"BLEU.Code,":[143],"models,":[144],"cases,":[145],"more":[147],"detailed":[148],"analysis":[149],"are":[150],"available":[151],"at":[152],"https://github.com/ReneeYe/XSTNet.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}