{"id":"https://openalex.org/W4375868881","doi":"https://doi.org/10.1109/icassp49357.2023.10095276","title":"Efficient Speech Translation with Dynamic Latent Perceivers","display_name":"Efficient Speech Translation with Dynamic Latent Perceivers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868881","doi":"https://doi.org/10.1109/icassp49357.2023.10095276"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095276","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/14925d66-02f9-442d-8f75-490e603206aa/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076257265","display_name":"Ioannis Tsiamas","orcid":"https://orcid.org/0000-0003-1049-2515"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Ioannis Tsiamas","raw_affiliation_strings":["Universitat Politècnica de Catalunya,Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de Catalunya,Barcelona","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014771820","display_name":"Gerard I. G\u00e1llego","orcid":null},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gerard I. G\u00e1llego","raw_affiliation_strings":["Universitat Politècnica de Catalunya,Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de Catalunya,Barcelona","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004224082","display_name":"Jos\u00e9 A. R. Fonollosa","orcid":"https://orcid.org/0000-0001-9513-7939"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 A. R. Fonollosa","raw_affiliation_strings":["Universitat Politècnica de Catalunya,Barcelona"],"affiliations":[{"raw_affiliation_string":"Universitat Politècnica de Catalunya,Barcelona","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074210163","display_name":"Marta R. Costa\u2010juss\u00e0","orcid":"https://orcid.org/0000-0002-5703-520X"},"institutions":[{"id":"https://openalex.org/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marta R. Costa-juss\u00e0","raw_affiliation_strings":["Meta AI,Paris","Meta AI, Paris"],"affiliations":[{"raw_affiliation_string":"Meta AI,Paris","institution_ids":["https://openalex.org/I190752583"]},{"raw_affiliation_string":"Meta AI, Paris","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5076257265"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":0.1758,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53461632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"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":0.9994999766349792,"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":0.9994000196456909,"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":0.7435263991355896},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6688443422317505},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6537225246429443},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5975422859191895},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5220425128936768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4319417178630829},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4157872200012207},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3907398581504822},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08244824409484863},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07064777612686157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435263991355896},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6688443422317505},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6537225246429443},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5975422859191895},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5220425128936768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4319417178630829},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4157872200012207},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3907398581504822},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08244824409484863},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07064777612686157},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095276","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/407408","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/407408","pdf_url":"https://upcommons.upc.edu/bitstreams/14925d66-02f9-442d-8f75-490e603206aa/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/407408","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/407408","pdf_url":"https://upcommons.upc.edu/bitstreams/14925d66-02f9-442d-8f75-490e603206aa/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375868881.pdf","grobid_xml":"https://content.openalex.org/works/W4375868881.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2567070169","https://openalex.org/W2892009249","https://openalex.org/W2899663614","https://openalex.org/W2908510526","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963532001","https://openalex.org/W2973048981","https://openalex.org/W2975381464","https://openalex.org/W3034625919","https://openalex.org/W3034772996","https://openalex.org/W3097777922","https://openalex.org/W3118578889","https://openalex.org/W3174446152","https://openalex.org/W3190965961","https://openalex.org/W3198959024","https://openalex.org/W4226275767","https://openalex.org/W4256701369","https://openalex.org/W4385245566","https://openalex.org/W6731370813","https://openalex.org/W6739901393","https://openalex.org/W6755977528","https://openalex.org/W6757817989","https://openalex.org/W6768080748","https://openalex.org/W6772381481","https://openalex.org/W6780226713","https://openalex.org/W6784050962","https://openalex.org/W6799838802","https://openalex.org/W6810311916","https://openalex.org/W6898505805","https://openalex.org/W6898634591"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2142795561","https://openalex.org/W2055243143","https://openalex.org/W4205302943","https://openalex.org/W4206178588","https://openalex.org/W3094491777","https://openalex.org/W3214715529","https://openalex.org/W4287635093"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"been":[2],"the":[3,30,34,55,64,101],"dominant":[4],"architecture":[5],"for":[6,41],"Speech":[7,45],"Translation":[8],"in":[9,15,44,48,110,135],"recent":[10],"years,":[11],"achieving":[12],"significant":[13,133],"improvements":[14],"translation":[16,136],"quality.":[17,137],"Since":[18],"speech":[19,65],"signals":[20],"are":[21],"longer":[22],"than":[23],"their":[24],"textual":[25],"counterparts,":[26],"and":[27,123],"due":[28],"to":[29,53,62,67,119],"quadratic":[31],"complexity":[32,56],"of":[33,78,103],"Transformer,":[35],"a":[36,59,68,75,113],"down-sampling":[37],"step":[38],"is":[39,116],"essential":[40],"its":[42],"adoption":[43],"Translation.":[46],"Instead,":[47],"this":[49],"research,":[50],"we":[51,73],"propose":[52],"ease":[54],"by":[57],"using":[58],"Perceiver":[60],"encoder":[61],"map":[63],"inputs":[66],"fixed-length":[69],"latent":[70,88],"representation.":[71],"Furthermore,":[72],"introduce":[74],"novel":[76],"way":[77],"training":[79],"Perceivers,":[80],"with":[81,97,128],"Dynamic":[82],"Latent":[83],"Access":[84],"(DLA),":[85],"unlocking":[86],"larger":[87],"spaces":[89],"without":[90,132],"any":[91],"additional":[92],"computational":[93,130],"overhead.":[94],"Speech-to-Text":[95],"Perceivers":[96],"DLA":[98,120],"can":[99,124],"match":[100],"performance":[102],"Transformer":[104],"baselines":[105],"across":[106],"three":[107],"language":[108],"pairs":[109],"MuST-C.":[111],"Finally,":[112],"DLA-trained":[114],"model":[115],"easily":[117],"adaptable":[118],"at":[121],"inference,":[122],"be":[125],"flexibly":[126],"deployed":[127],"various":[129],"budgets,":[131],"drops":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}