{"id":"https://openalex.org/W4412944384","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.14","title":"HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation","display_name":"HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944384","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.14"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.iwslt-1.14","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.14","pdf_url":"https://aclanthology.org/2025.iwslt-1.14.pdf","source":{"id":"https://openalex.org/S7407087070","display_name":"International Conference on Spoken Language Translation (IWSLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.iwslt-1.14.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014592910","display_name":"Amir Hussein","orcid":"https://orcid.org/0000-0002-0820-4062","observed_orcids":["https://orcid.org/0000-0002-0820-4062"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amir Hussein","raw_affiliation_strings":["JHU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JHU","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101215727","display_name":"Cihan Xiao","orcid":"https://orcid.org/0009-0006-6262-3213","observed_orcids":["https://orcid.org/0009-0006-6262-3213"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cihan Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738","observed_orcids":["https://orcid.org/0000-0001-8653-7738"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["JHU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JHU","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089659636","display_name":"Dan Povey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Povey","raw_affiliation_strings":["JHU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JHU","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059858850","display_name":"Leibny Paola Garcia","orcid":"https://orcid.org/0000-0002-7449-5726","observed_orcids":["https://orcid.org/0000-0002-7449-5726"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leibny Paola Garcia Perera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev P. Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897","observed_orcids":["https://orcid.org/0000-0001-5976-0897"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["HLTCOE/CLSP JHU"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HLTCOE/CLSP JHU","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7133,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71654306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"153","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/neural-transducer","display_name":"neural transducer","score":0.9679999947547913},{"id":"https://openalex.org/keywords/speech-translation","display_name":"speech translation","score":0.6830000281333923},{"id":"https://openalex.org/keywords/self-distillation","display_name":"self-distillation","score":0.9750000238418579},{"id":"https://openalex.org/keywords/word-reordering","display_name":"word reordering","score":0.8859999775886536},{"id":"https://openalex.org/keywords/hierarchical-encoder","display_name":"hierarchical encoder","score":0.8489999771118164},{"id":"https://openalex.org/keywords/computational-efficiency","display_name":"computational efficiency","score":0.6499999761581421},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic language","score":0.5249999761581421},{"id":"https://openalex.org/keywords/spanish-language","display_name":"Spanish language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/mandarin","display_name":"mandarin","score":1.0}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71100252866745},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6333989500999451},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.6160699725151062},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6055947542190552},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5673690438270569},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5431557893753052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4186711609363556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38544198870658875},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2017216980457306},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14640220999717712},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09098213911056519},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05659034848213196},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.iwslt-1.14","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.14","pdf_url":"https://aclanthology.org/2025.iwslt-1.14.pdf","source":{"id":"https://openalex.org/S7407087070","display_name":"International Conference on Spoken Language Translation (IWSLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.02157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.02157","pdf_url":"https://arxiv.org/pdf/2506.02157","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.02157","doi":"https://doi.org/10.48550/arxiv.2506.02157","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.02157","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.iwslt-1.14","doi":"https://doi.org/10.18653/v1/2025.iwslt-1.14","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.iwslt-1.14","pdf_url":"https://aclanthology.org/2025.iwslt-1.14.pdf","source":{"id":"https://openalex.org/S7407087070","display_name":"International Conference on Spoken Language Translation (IWSLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944384.pdf","grobid_xml":"https://content.openalex.org/works/W4412944384.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W4394972992","https://openalex.org/W4402112050","https://openalex.org/W4403324091"],"related_works":["https://openalex.org/W4224137820","https://openalex.org/W4391021779","https://openalex.org/W7166881359","https://openalex.org/W2998386507","https://openalex.org/W3160054295","https://openalex.org/W4392910316","https://openalex.org/W4408354344","https://openalex.org/W4288817190","https://openalex.org/W4402671596","https://openalex.org/W4416799628"],"abstract_inverted_index":{"Neural":[0,71],"transducers":[1],"(NT)":[2],"provide":[3],"an":[4],"effective":[5],"framework":[6,80],"for":[7,73],"speech":[8,15,23],"streaming,":[9],"demonstrating":[10],"strong":[11],"performance":[12,36,160],"in":[13,45],"automatic":[14],"recognition":[16],"(ASR).However,":[17],"the":[18,167],"application":[19],"of":[20],"NT":[21,162],"to":[22,87,129],"translation":[24,85,144],"(ST)":[25],"remains":[26],"challenging,":[27],"as":[28],"existing":[29],"approaches":[30,55],"struggle":[31],"with":[32,48,101,169],"word":[33],"reordering":[34],"and":[35,42,76,84,124,142,155,164],"degradation":[37],"when":[38],"jointly":[39],"modeling":[40],"ASR":[41,83,96,114],"ST,":[43],"resulting":[44],"a":[46,78,117,121,125,135],"gap":[47,168],"attention-based":[49],"encoder-decoder":[50],"(AED)":[51],"models.Existing":[52],"NT-based":[53],"ST":[54,93],"also":[56],"suffer":[57],"from":[58,113],"high":[59],"computational":[60,107],"training":[61,131],"costs.To":[62],"address":[63],"these":[64],"issues,":[65],"we":[66,98,105,133],"propose":[67],"HENT-SRT":[68],"(Hierarchical":[69],"Efficient":[70],"Transducer":[72],"Speech":[74],"Recognition":[75],"Translation),":[77],"novel":[79],"that":[81],"factorizes":[82],"tasks":[86],"better":[88],"handle":[89],"reordering.To":[90],"ensure":[91],"robust":[92],"while":[94],"preserving":[95],"performance,":[97],"use":[99],"self-distillation":[100],"CTC":[102],"consistency":[103],"regularization.Moreover,":[104],"improve":[106],"efficiency":[108],"by":[109],"incorporating":[110],"best":[111],"practices":[112],"transducers,":[115],"including":[116],"downsampled":[118],"hierarchical":[119],"encoder,":[120],"stateless":[122],"predictor,":[123],"pruned":[126],"transducer":[127],"loss":[128],"reduce":[130],"complexity.Finally,":[132],"introduce":[134],"blank":[136],"penalty":[137],"during":[138],"decoding,":[139],"reducing":[140],"deletions":[141],"improving":[143],"quality.Our":[145],"approach":[146],"is":[147],"evaluated":[148],"on":[149],"three":[150],"conversational":[151],"datasets":[152],"Arabic,":[153],"Spanish,":[154],"Mandarin":[156],"achieving":[157],"new":[158],"state-of-the-art":[159],"among":[161],"models":[163],"substantially":[165],"narrowing":[166],"AED-based":[170],"systems.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}