{"id":"https://openalex.org/W2605131327","doi":"https://doi.org/10.21437/interspeech.2017-503","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","display_name":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2605131327","doi":"https://doi.org/10.21437/interspeech.2017-503","mag":"2605131327"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000408865","display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112445699","display_name":"Navdeep Jaitly","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Navdeep Jaitly","raw_affiliation_strings":["Nvidia"],"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010253402","display_name":"Yonghui Wu","orcid":"https://orcid.org/0000-0002-6780-6135"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghui Wu","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100715424","display_name":"Zhifeng Chen","orcid":"https://orcid.org/0000-0001-8631-2424"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhifeng Chen","raw_affiliation_strings":["Google Brain"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103273436"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":21.5518,"has_fulltext":false,"cited_by_count":260,"citation_normalized_percentile":{"value":0.9949201,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2625","last_page":"2629"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9984999895095825,"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":0.9944999814033508,"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/sequence","display_name":"Sequence (biology)","score":0.7611818909645081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7212756276130676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5035209059715271},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5023465156555176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3918626606464386}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7611818909645081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7212756276130676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5035209059715271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5023465156555176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3918626606464386},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2017-503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-503","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1485009520","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1537859740","https://openalex.org/W1836465849","https://openalex.org/W1869752048","https://openalex.org/W1895577753","https://openalex.org/W1970987322","https://openalex.org/W2011783148","https://openalex.org/W2095705004","https://openalex.org/W2113106066","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2136530135","https://openalex.org/W2139647714","https://openalex.org/W2251313925","https://openalex.org/W2252212004","https://openalex.org/W2327501763","https://openalex.org/W2375583958","https://openalex.org/W2466918907","https://openalex.org/W2525778437","https://openalex.org/W2530876040","https://openalex.org/W2550821151","https://openalex.org/W2577366047","https://openalex.org/W2593011301","https://openalex.org/W2949328740","https://openalex.org/W2953384591","https://openalex.org/W2963842982","https://openalex.org/W2964102148","https://openalex.org/W3012492057","https://openalex.org/W4294150926"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880","https://openalex.org/W3192589309"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,48,97,141,149],"recurrent":[3],"encoder-decoder":[4],"deep":[5],"neural":[6],"network":[7,144],"architecture":[8,54],"that":[9,55,65,121],"directly":[10],"translates":[11],"speech":[12,26,61,93,103,135],"in":[13,18,29,128],"one":[14],"language":[15,43],"into":[16,27],"text":[17,28],"another.The":[19],"model":[20,82],"does":[21,34],"not":[22],"explicitly":[23],"transcribe":[24],"the":[25,30,39,76,89,114,125],"source":[31,42],"language,":[32],"nor":[33],"it":[35,66],"require":[36],"supervision":[37],"from":[38],"ground":[40],"truth":[41],"transcription":[44],"during":[45],"training.We":[46],"apply":[47],"slightly":[49],"modified":[50],"sequence-to-sequence":[51,102,134],"with":[52,140],"attention":[53],"has":[56],"previously":[57],"been":[58],"used":[59],"for":[60,70],"recognition":[62,104,138],"and":[63,105,137],"show":[64],"can":[67,145],"be":[68],"repurposed":[69],"this":[71],"more":[72],"complex":[73],"task,":[74,95],"illustrating":[75],"power":[77],"of":[78,99,124],"attention-based":[79],"models.A":[80],"single":[81],"trained":[83,101],"end-to-end":[84],"obtains":[85],"state-of-the-art":[86],"performance":[87,147],"on":[88,113],"Fisher":[90,115],"Callhome":[91],"Spanish-English":[92],"translation":[94,107,136],"outperforming":[96],"cascade":[98],"independently":[100],"machine":[106],"models":[108,139],"by":[109,131,148],"1.8":[110],"BLEU":[111,152],"points":[112],"test":[116],"set.In":[117],"addition,":[118],"we":[119],"find":[120],"making":[122],"use":[123],"training":[126,133],"data":[127],"both":[129],"languages":[130],"multi-task":[132],"shared":[142],"encoder":[143],"improve":[146],"further":[150],"1.4":[151],"points.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":45},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":47},{"year":2020,"cited_by_count":52},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
