{"id":"https://openalex.org/W2920166246","doi":"https://doi.org/10.1109/icassp.2019.8683069","title":"Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese","display_name":"Models of Visually Grounded Speech Signal Pay Attention to Nouns: A Bilingual Experiment on English and Japanese","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2920166246","doi":"https://doi.org/10.1109/icassp.2019.8683069","mag":"2920166246"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/1902.03052","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008481817","display_name":"William N. Havard","orcid":"https://orcid.org/0000-0002-1226-4156"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210160287","display_name":"Laboratoire de Linguistique et Didactique des Langues Etrang\u00e8res et Maternelles","ror":"https://ror.org/05588ks88","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210139971","https://openalex.org/I4210150872","https://openalex.org/I4210160287","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"William N. Havard","raw_affiliation_strings":["LIG, Univ. Grenoble Alpes, CNRS, Grenoble, 38000, France","GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","LIDILEM  - LInguistique et DIdactique des Langues \u00c9trang\u00e8res et Maternelles (B\u00e2timent Stendhal - CS40700 - 38058 Grenoble cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIG, Univ. Grenoble Alpes, CNRS, Grenoble, 38000, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I1294671590","https://openalex.org/I899635006"]},{"raw_affiliation_string":"GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I4210104430"]},{"raw_affiliation_string":"LIDILEM  - LInguistique et DIdactique des Langues \u00c9trang\u00e8res et Maternelles (B\u00e2timent Stendhal - CS40700 - 38058 Grenoble cedex 9 - France)","institution_ids":["https://openalex.org/I4210160287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087788538","display_name":"Jean\u2010Pierre Chevrot","orcid":"https://orcid.org/0000-0003-0883-9321"},"institutions":[{"id":"https://openalex.org/I4210160287","display_name":"Laboratoire de Linguistique et Didactique des Langues Etrang\u00e8res et Maternelles","ror":"https://ror.org/05588ks88","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210139971","https://openalex.org/I4210150872","https://openalex.org/I4210160287","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Pierre Chevrot","raw_affiliation_strings":["LIDILEM, Univ. Grenoble Alpes, Grenoble, 38000, France","LIDILEM  - LInguistique et DIdactique des Langues \u00c9trang\u00e8res et Maternelles (B\u00e2timent Stendhal - CS40700 - 38058 Grenoble cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIDILEM, Univ. Grenoble Alpes, Grenoble, 38000, France","institution_ids":["https://openalex.org/I4210160287","https://openalex.org/I899635006"]},{"raw_affiliation_string":"LIDILEM  - LInguistique et DIdactique des Langues \u00c9trang\u00e8res et Maternelles (B\u00e2timent Stendhal - CS40700 - 38058 Grenoble cedex 9 - France)","institution_ids":["https://openalex.org/I4210160287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040820339","display_name":"Laurent Besacier","orcid":"https://orcid.org/0000-0001-7411-9125"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Besacier","raw_affiliation_strings":["LIG, Univ. Grenoble Alpes, CNRS, Grenoble, 38000, France","GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIG, Univ. Grenoble Alpes, CNRS, Grenoble, 38000, France","institution_ids":["https://openalex.org/I4210104430","https://openalex.org/I1294671590","https://openalex.org/I899635006"]},{"raw_affiliation_string":"GETALP  - Groupe d\u2019\u00c9tude en Traduction Automatique/Traitement Automatis\u00e9 des Langues et de la Parole (Laboratoire LIG - B\u00e2timent IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9  - France)","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I4210104430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1332,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.90094473,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8618","last_page":"8622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9939000010490417,"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/T12031","display_name":"Speech and dialogue systems","score":0.9872000217437744,"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/parallels","display_name":"Parallels","score":0.7319658398628235},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6942235231399536},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.6210360527038574},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4768587052822113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.441017210483551},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42072510719299316},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4037525951862335}],"concepts":[{"id":"https://openalex.org/C2775922551","wikidata":"https://www.wikidata.org/wiki/Q7135033","display_name":"Parallels","level":2,"score":0.7319658398628235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6942235231399536},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.6210360527038574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4768587052822113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.441017210483551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42072510719299316},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4037525951862335},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2019.8683069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1902.03052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.03052","pdf_url":"https://arxiv.org/pdf/1902.03052","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":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02013984v1","is_oa":true,"landing_page_url":"https://hal.science/hal-02013984","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, United Kingdom. pp.8618-8622, ⟨10.1109/ICASSP.2019.8683069⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1902.03052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.03052","pdf_url":"https://arxiv.org/pdf/1902.03052","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1041279674","display_name":"MIAI @ Grenoble Alpes","funder_award_id":"ANR-19-P3IA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G6175499886","display_name":"Systemes et Algorithmes Pervasifs au confluent des mondes physique et num\u00e9rique","funder_award_id":"ANR-11-LABX-0025","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":40,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2023182894","https://openalex.org/W2127863960","https://openalex.org/W2137010615","https://openalex.org/W2143995218","https://openalex.org/W2147682057","https://openalex.org/W2185175083","https://openalex.org/W2216809352","https://openalex.org/W2292919134","https://openalex.org/W2483390977","https://openalex.org/W2556930864","https://openalex.org/W2580178245","https://openalex.org/W2586148577","https://openalex.org/W2586602577","https://openalex.org/W2601713192","https://openalex.org/W2611064105","https://openalex.org/W2625455707","https://openalex.org/W2736876693","https://openalex.org/W2738919465","https://openalex.org/W2747874407","https://openalex.org/W2796156786","https://openalex.org/W2796315435","https://openalex.org/W2962753610","https://openalex.org/W2962832640","https://openalex.org/W2962835968","https://openalex.org/W2962862718","https://openalex.org/W2963330681","https://openalex.org/W2963496089","https://openalex.org/W2963778889","https://openalex.org/W2963902314","https://openalex.org/W2964001192","https://openalex.org/W3099142230","https://openalex.org/W3105148948","https://openalex.org/W6637373629","https://openalex.org/W6679101406","https://openalex.org/W6681262047","https://openalex.org/W6681871837","https://openalex.org/W6729977899","https://openalex.org/W6743149223"],"related_works":["https://openalex.org/W2277794996","https://openalex.org/W1964879957","https://openalex.org/W2504593154","https://openalex.org/W2005046750","https://openalex.org/W4390115938","https://openalex.org/W2808752767","https://openalex.org/W2807806191","https://openalex.org/W1534056076","https://openalex.org/W4210798000","https://openalex.org/W3198256891"],"abstract_inverted_index":{"We":[0,39],"investigate":[1,69],"the":[2,87,101],"behaviour":[3,30],"of":[4,9],"attention":[5,24,46,49,54],"in":[6],"neural":[7,45,53],"models":[8,75],"visually":[10,72],"grounded":[11,73],"speech":[12],"trained":[13],"on":[14,26,56],"two":[15,34,71],"languages:":[16],"English":[17],"and":[18,28,47,50,95],"Japanese.":[19],"Experimental":[20],"results":[21],"show":[22,51],"that":[23,52],"focuses":[25,55],"nouns":[27],"this":[29],"holds":[31],"true":[32],"for":[33,64,103],"very":[35],"typologically":[36],"different":[37],"languages.":[38],"also":[40],"draw":[41],"parallels":[42],"between":[43],"artificial":[44],"human":[48,65],"word":[57],"endings":[58],"as":[59],"it":[60],"has":[61],"been":[62],"theorised":[63],"attention.":[66],"Finally,":[67],"we":[68],"how":[70],"monolingual":[74],"can":[76],"be":[77],"used":[78],"to":[79,100],"perform":[80],"cross-lingual":[81],"speech-to-speech":[82],"retrieval.":[83],"For":[84],"both":[85],"languages,":[86],"enriched":[88],"bilingual":[89],"(speech-image)":[90],"corpora":[91],"with":[92],"part-of-speech":[93],"tags":[94],"forced":[96],"alignments":[97],"are":[98],"distributed":[99],"community":[102],"reproducible":[104],"research.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}