{"id":"https://openalex.org/W3093981744","doi":"https://doi.org/10.1109/icassp39728.2021.9413719","title":"Cascaded Models with Cyclic Feedback for Direct Speech Translation","display_name":"Cascaded Models with Cyclic Feedback for Direct Speech Translation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3093981744","doi":"https://doi.org/10.1109/icassp39728.2021.9413719","mag":"3093981744"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.11153","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041285596","display_name":"Tsz Kin Lam","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tsz Kin Lam","raw_affiliation_strings":["Computational Linguistics, Germany","Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Computational Linguistics, Germany","institution_ids":[]},{"raw_affiliation_string":"Heidelberg University","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068853519","display_name":"Shigehiko Schamoni","orcid":"https://orcid.org/0000-0002-0304-2412"},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shigehiko Schamoni","raw_affiliation_strings":["Computational Linguistics, Germany","IWR, Heidelberg University, Germany","Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Computational Linguistics, Germany","institution_ids":[]},{"raw_affiliation_string":"IWR, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University","institution_ids":["https://openalex.org/I223822909"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011749347","display_name":"Stefan Riezler","orcid":null},"institutions":[{"id":"https://openalex.org/I223822909","display_name":"Heidelberg University","ror":"https://ror.org/038t36y30","country_code":"DE","type":"education","lineage":["https://openalex.org/I223822909"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Riezler","raw_affiliation_strings":["Computational Linguistics, Germany","IWR, Heidelberg University, Germany","Heidelberg University"],"affiliations":[{"raw_affiliation_string":"Computational Linguistics, Germany","institution_ids":[]},{"raw_affiliation_string":"IWR, Heidelberg University, Germany","institution_ids":["https://openalex.org/I223822909"]},{"raw_affiliation_string":"Heidelberg University","institution_ids":["https://openalex.org/I223822909"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041285596"],"corresponding_institution_ids":["https://openalex.org/I223822909"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00907484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7508","last_page":"7512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.8594173789024353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8526022434234619},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6228059530258179},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6148665547370911},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5674708485603333},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5353525280952454},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5203765630722046},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.5145203471183777},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5085252523422241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4721163511276245},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.45372796058654785},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.41238918900489807},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06872829794883728}],"concepts":[{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.8594173789024353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8526022434234619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6228059530258179},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6148665547370911},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5674708485603333},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5353525280952454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5203765630722046},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.5145203471183777},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5085252523422241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4721163511276245},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.45372796058654785},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.41238918900489807},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06872829794883728},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.11153","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11153","pdf_url":"https://arxiv.org/pdf/2010.11153","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3093981744","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.11153.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.11153","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.11153","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.17023/cbk3-6y40","is_oa":true,"landing_page_url":"https://doi.org/10.17023/cbk3-6y40","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.11153","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.11153","pdf_url":"https://arxiv.org/pdf/2010.11153","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W399167303","https://openalex.org/W854541894","https://openalex.org/W2010917994","https://openalex.org/W2101105183","https://openalex.org/W2114483840","https://openalex.org/W2146574666","https://openalex.org/W2186089609","https://openalex.org/W2250342921","https://openalex.org/W2466918907","https://openalex.org/W2605131327","https://openalex.org/W2782717521","https://openalex.org/W2786891429","https://openalex.org/W2936969148","https://openalex.org/W2962832505","https://openalex.org/W2963250244","https://openalex.org/W2963266340","https://openalex.org/W2963285578","https://openalex.org/W2963400424","https://openalex.org/W2963403868","https://openalex.org/W2963779652","https://openalex.org/W2964104866","https://openalex.org/W2964161387","https://openalex.org/W2968831808","https://openalex.org/W2972448360","https://openalex.org/W2982129078","https://openalex.org/W3007142233","https://openalex.org/W3016256870","https://openalex.org/W3029944303","https://openalex.org/W3030437843","https://openalex.org/W3032433061","https://openalex.org/W3034625919","https://openalex.org/W6623517193","https://openalex.org/W6685562342","https://openalex.org/W6686989717","https://openalex.org/W6688167117","https://openalex.org/W6739901393","https://openalex.org/W6742632731","https://openalex.org/W6751792830","https://openalex.org/W6769089506","https://openalex.org/W6769269733","https://openalex.org/W6771467084","https://openalex.org/W6773238793","https://openalex.org/W6775467270","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W3018778770","https://openalex.org/W2122511433","https://openalex.org/W1761757934","https://openalex.org/W2973107548","https://openalex.org/W3163239510","https://openalex.org/W2982129078","https://openalex.org/W3185037272","https://openalex.org/W2152403569","https://openalex.org/W90894508","https://openalex.org/W3180526677","https://openalex.org/W3169172723","https://openalex.org/W2002870480","https://openalex.org/W2010917994","https://openalex.org/W3186513069","https://openalex.org/W3196833881","https://openalex.org/W1971352820","https://openalex.org/W194878845","https://openalex.org/W3185685802","https://openalex.org/W2400297987","https://openalex.org/W2041174201"],"abstract_inverted_index":{"Direct":[0],"speech":[1,8,29,40,102,133],"translation":[2,34,41,103],"describes":[3],"a":[4,22,58,72],"scenario":[5],"where":[6,61],"only":[7],"inputs":[9],"and":[10,32,48,54,81,109,123],"corresponding":[11],"translations":[12],"are":[13,17],"available.":[14],"Such":[15],"data":[16,42,112],"notoriously":[18],"limited.":[19],"We":[20],"present":[21],"technique":[23],"that":[24],"allows":[25],"cascades":[26],"of":[27,65,106,115],"automatic":[28],"recognition":[30],"(ASR)":[31],"machine":[33],"(MT)":[35],"to":[36,45,74,100,117,125],"exploit":[37],"in-domain":[38],"direct":[39],"in":[43],"addition":[44],"out-of-domain":[46],"MT":[47,53,67,83],"ASR":[49,77,89],"data.":[50],"After":[51],"pre-training":[52],"ASR,":[55],"we":[56],"use":[57],"feed-back":[59],"cycle":[60],"the":[62,66,76,82,110],"downstream":[63],"performance":[64],"system":[68,78],"is":[69,85],"used":[70],"as":[71],"signal":[73],"improve":[75],"by":[79],"self-training,":[80],"component":[84],"fine-tuned":[86],"on":[87,121,129],"multiple":[88],"outputs,":[90],"making":[91],"it":[92],"more":[93],"tolerant":[94],"towards":[95],"spelling":[96],"variations.":[97],"A":[98],"comparison":[99],"end-to-end":[101],"using":[104],"components":[105],"identical":[107],"architecture":[108],"same":[111],"shows":[113],"gains":[114],"up":[116,124],"3.8":[118],"BLEU":[119,127],"points":[120,128],"LibriVoxDeEn":[122],"5.1":[126],"CoVoST":[130],"for":[131],"German-to-English":[132],"translation.":[134]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}