{"id":"https://openalex.org/W3126870998","doi":"https://doi.org/10.1109/icassp39728.2021.9413581","title":"End2End Acoustic to Semantic Transduction","display_name":"End2End Acoustic to Semantic Transduction","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3126870998","doi":"https://doi.org/10.1109/icassp39728.2021.9413581","mag":"3126870998"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413581","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":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.01013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060151795","display_name":"Valentin Pelloin","orcid":"https://orcid.org/0000-0002-1259-127X"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Valentin Pelloin","raw_affiliation_strings":["Le Mans University,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Le Mans University,LIUM,France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056103113","display_name":"Nathalie Camelin","orcid":"https://orcid.org/0000-0001-6786-1372"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nathalie Camelin","raw_affiliation_strings":["Le Mans University,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Le Mans University,LIUM,France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025212823","display_name":"Antoine Laurent","orcid":"https://orcid.org/0000-0002-2653-1008"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Laurent","raw_affiliation_strings":["Le Mans University,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Le Mans University,LIUM,France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081408760","display_name":"Renato De Mori","orcid":"https://orcid.org/0000-0002-2083-9095"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Renato De Mori","raw_affiliation_strings":["Avignon University,LIA,France","Laboratoire Informatique d'Avignon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon University,LIA,France","institution_ids":["https://openalex.org/I4210119991"]},{"raw_affiliation_string":"Laboratoire Informatique d'Avignon","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081219569","display_name":"Antoine Caubri\u00e8re","orcid":null},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Caubriere","raw_affiliation_strings":["Le Mans University,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Le Mans University,LIUM,France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081852717","display_name":"Yannick Est\u00e8ve","orcid":"https://orcid.org/0000-0002-3656-8883"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Esteve","raw_affiliation_strings":["Avignon University,LIA,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avignon University,LIA,France","institution_ids":["https://openalex.org/I4210119991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075235121","display_name":"Sylvain Meignier","orcid":"https://orcid.org/0000-0001-7687-073X"},"institutions":[{"id":"https://openalex.org/I234216984","display_name":"Universit\u00e9 Nantes Angers Le Mans","ror":"https://ror.org/0406t3m57","country_code":"FR","type":"education","lineage":["https://openalex.org/I234216984"]},{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Meignier","raw_affiliation_strings":["Le Mans University,LIUM,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Le Mans University,LIUM,France","institution_ids":["https://openalex.org/I234216984","https://openalex.org/I4210108471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0896,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.80789118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7448","last_page":"7452"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.7156421542167664},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6318476796150208},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6281096339225769},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5958846211433411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5296452045440674},{"id":"https://openalex.org/keywords/transduction","display_name":"Transduction (biophysics)","score":0.5009970664978027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4702785313129425},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.424124538898468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7156421542167664},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6318476796150208},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6281096339225769},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5958846211433411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5296452045440674},{"id":"https://openalex.org/C15152581","wikidata":"https://www.wikidata.org/wiki/Q7833966","display_name":"Transduction (biophysics)","level":2,"score":0.5009970664978027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4702785313129425},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.424124538898468},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413581","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:2102.01013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.01013","pdf_url":"https://arxiv.org/pdf/2102.01013","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":"pmh:oai:HAL:hal-03128163v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03128163","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, ON, Canada. ⟨10.1109/ICASSP39728.2021.9413581⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.01013","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.01013","pdf_url":"https://arxiv.org/pdf/2102.01013","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":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1663281917","display_name":"Artificial Intelligence foR Semantically controlled SPEech UndeRstanding","funder_award_id":"ANR-19-CE23-0004","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W204182981","https://openalex.org/W1586532344","https://openalex.org/W1649407914","https://openalex.org/W1915251500","https://openalex.org/W2010470211","https://openalex.org/W2123379364","https://openalex.org/W2133564696","https://openalex.org/W2251580867","https://openalex.org/W2327501763","https://openalex.org/W2400835843","https://openalex.org/W2473329891","https://openalex.org/W2575101493","https://openalex.org/W2618015847","https://openalex.org/W2786839803","https://openalex.org/W2886180730","https://openalex.org/W2894164357","https://openalex.org/W2914417638","https://openalex.org/W2962826786","https://openalex.org/W2963288440","https://openalex.org/W2963974889","https://openalex.org/W2964308564","https://openalex.org/W2972327934","https://openalex.org/W2979476256","https://openalex.org/W2996383576","https://openalex.org/W3005910077","https://openalex.org/W3008912312","https://openalex.org/W3015412890","https://openalex.org/W3015700086","https://openalex.org/W3015797571","https://openalex.org/W3032892481","https://openalex.org/W3035202887","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4240043473","https://openalex.org/W6608208975","https://openalex.org/W6635078382","https://openalex.org/W6640059789","https://openalex.org/W6679434410","https://openalex.org/W6691675912","https://openalex.org/W6713313444","https://openalex.org/W6732187701","https://openalex.org/W6748263443","https://openalex.org/W6769196770","https://openalex.org/W6779199192"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2405439032","https://openalex.org/W2132658536","https://openalex.org/W2070212102","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036","https://openalex.org/W2124470186"],"abstract_inverted_index":{"In":[0],"this":[1,53],"paper,":[2],"we":[3],"propose":[4],"a":[5,48,56,100,104],"novel":[6],"end-to-end":[7],"sequence-to-sequence":[8],"spoken":[9],"language":[10,51],"understanding":[11],"model":[12,88],"using":[13],"an":[14,63,76,86],"attention":[15],"mechanism.":[16],"It":[17],"reliably":[18],"selects":[19],"contextual":[20],"acoustic":[21,41],"features":[22],"in":[23],"order":[24],"to":[25,82],"hypothesize":[26],"semantic":[27],"contents.":[28],"An":[29],"initial":[30],"architecture":[31],"capable":[32],"of":[33,111],"extracting":[34],"all":[35],"pronounced":[36],"words":[37],"and":[38,45,62,94,103],"concepts":[39,93],"from":[40],"spans":[42],"is":[43,89],"designed":[44],"tested.":[46],"With":[47],"shallow":[49],"fusion":[50],"model,":[52],"system":[54],"reaches":[55,99],"13.6":[57],"concept":[58,65],"error":[59,67],"rate":[60,68],"(CER)":[61],"18.5":[64],"value":[66],"(CVER)":[69],"on":[70],"the":[71,83],"French":[72],"MEDIA":[73],"corpus,":[74],"achieving":[75],"absolute":[77],"2.8":[78],"points":[79],"reduction":[80],"compared":[81],"state-of-the-art.":[84],"Then,":[85],"original":[87],"proposed":[90],"for":[91],"hypothesizing":[92],"their":[95],"values.":[96],"This":[97],"transduction":[98],"15.4":[101],"CER":[102],"21.6":[105],"CVER":[106],"without":[107],"any":[108],"new":[109],"type":[110],"context.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}