{"id":"https://openalex.org/W4224137820","doi":"https://doi.org/10.21437/interspeech.2022-10953","title":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","display_name":"Large-Scale Streaming End-to-End Speech Translation with Neural Transducers","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4224137820","doi":"https://doi.org/10.21437/interspeech.2022-10953"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10953","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10953","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/A5111701041","display_name":"Jian Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jian Xue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peidong Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108266978","display_name":"Matt Post","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matt Post","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111701041"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0876,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88874755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3263","last_page":"3267"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9977999925613403,"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/T11309","display_name":"Music and Audio Processing","score":0.9736999869346619,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6569327712059021},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6437729597091675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4737685024738312},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45781201124191284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19792664051055908},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061571747064590454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6569327712059021},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6437729597091675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4737685024738312},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45781201124191284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19792664051055908},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061571747064590454},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10953","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10953","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2001405890","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Neural":[0],"transducers":[1],"have":[2],"been":[3],"widely":[4],"used":[5],"in":[6,31,83],"automatic":[7],"speech":[8,20,60],"recognition":[9],"(ASR).":[10],"In":[11,85],"this":[12],"paper,":[13],"we":[14,75,87],"introduce":[15],"it":[16],"to":[17,25,29,68,91],"streaming":[18],"end-to-end":[19],"translation":[21,46],"(ST),":[22],"which":[23,94],"aims":[24],"convert":[26],"audio":[27],"signals":[28],"texts":[30,96],"other":[32],"languages":[33,99],"directly.":[34],"Compared":[35],"with":[36],"cascaded":[37,130],"ST":[38,53,90,119,131],"that":[39,117],"performs":[40],"ASR":[41,67],"followed":[42],"by":[43],"text-based":[44],"machine":[45],"(MT),":[47],"the":[48,72,80,101],"proposed":[49],"Transformer":[50],"transducer":[51],"(TT)-based":[52],"model":[54],"drastically":[55],"reduces":[56,123],"inference":[57,124],"latency,":[58],"exploits":[59],"information,":[61],"and":[62],"avoids":[63],"error":[64],"propagation":[65],"from":[66],"MT.":[69],"To":[70],"improve":[71],"modeling":[73],"capacity,":[74],"propose":[76],"attention":[77],"pooling":[78],"for":[79,132],"joint":[81],"network":[82],"TT.":[84],"addition,":[86],"extend":[88],"TT-based":[89,118],"multilingual":[92],"ST,":[93],"generates":[95],"of":[97],"multiple":[98],"at":[100],"same":[102],"time.":[103],"Experimental":[104],"results":[105],"on":[106],"a":[107],"large-scale":[108],"50":[109],"thousand":[110],"(K)":[111],"hours":[112],"pseudo-labeled":[113],"training":[114],"set":[115],"show":[116],"not":[120],"only":[121],"significantly":[122],"time":[125],"but":[126],"also":[127],"outperforms":[128],"non-streaming":[129],"English-German":[133],"translation.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}