{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/124231"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/124231","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Towards multilingual lexicon discovery from visually grounded speech","abstract":"In this thesis, we present a method for the discovery of word-like units and their approximate translations from visually grounded speech across multiple languages. We first train a neural network model to map images and their spoken audio captions in both English and Hindi to a shared, multimodal embedding space. Next, we use this model to segment and cluster regions of the spoken captions which approximately correspond to words. Then, we exploit between-cluster similarities in the embedding space to associate English pseudo-word clusters with Hindi pseudo-word clusters, and show that many of these cluster pairings capture semantic translations between English and Hindi words. We present quantitative cross-lingual clustering results, as well as qualitative results in the form of a bilingual picture dictionary. Finally, we show the same analysis for a joint training using three languages at the same time, with Japanese as the third language.","abstract_html":"In this thesis, we present a method for the discovery of word-like units and their approximate translations from visually grounded speech across multiple languages. We first train a neural network model to map images and their spoken audio captions in both English and Hindi to a shared, multimodal embedding space. Next, we use this model to segment and cluster regions of the spoken captions which approximately correspond to words. Then, we exploit between-cluster similarities in the embedding space to associate English pseudo-word clusters with Hindi pseudo-word clusters, and show that many of these cluster pairings capture semantic translations between English and Hindi words. We present quantitative cross-lingual clustering results, as well as qualitative results in the form of a bilingual picture dictionary. Finally, we show the same analysis for a joint training using three languages at the same time, with Japanese as the third language.","abstract_has_math":false,"creators":["Azuh, Emmanuel Mensah"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["James R. Glass and David Harwath."],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-07-22T22:21:49Z","subjects":["Electrical Engineering and Computer Science."],"languages":["eng"],"rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"rights_urls":["http://dspace.mit.edu/handle/1721.1/7582"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/124231","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["James R. Glass and David Harwath."]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."]},{"key":"dc:creator","label":"Author","values":["Azuh, Emmanuel Mensah"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-03-24T15:35:27Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-03-24T15:35:27Z"]},{"key":"dc:date.issued","label":"Date","values":["2019"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electrical Engineering and Computer Science."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://dspace.mit.edu/handle/1721.1/7582"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/124231"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 99-103)."]},{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, we present a method for the discovery of word-like units and their approximate translations from visually grounded speech across multiple languages. We first train a neural network model to map images and their spoken audio captions in both English and Hindi to a shared, multimodal embedding space. Next, we use this model to segment and cluster regions of the spoken captions which approximately correspond to words. Then, we exploit between-cluster similarities in the embedding space to associate English pseudo-word clusters with Hindi pseudo-word clusters, and show that many of these cluster pairings capture semantic translations between English and Hindi words. We present quantitative cross-lingual clustering results, as well as qualitative results in the form of a bilingual picture dictionary. Finally, we show the same analysis for a joint training using three languages at the same time, with Japanese as the third language."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M. Eng."]},{"key":"dc:title","label":"Title","values":["Towards multilingual lexicon discovery from visually grounded speech"]}]}],"canonical_facts":{"dc:contributor.advisor":["James R. Glass and David Harwath."],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","EECS"],"dc:contributor.other":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science."],"dc:creator":["Azuh, Emmanuel Mensah"],"dc:date.accessioned":["2020-03-24T15:35:27Z"],"dc:date.available":["2020-03-24T15:35:27Z"],"dc:date.issued":["2019"],"dc:description":["This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.","Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019","Cataloged from student-submitted PDF version of thesis.","Includes bibliographical references (pages 99-103)."],"dc:description.abstract":["In this thesis, we present a method for the discovery of word-like units and their approximate translations from visually grounded speech across multiple languages. We first train a neural network model to map images and their spoken audio captions in both English and Hindi to a shared, multimodal embedding space. Next, we use this model to segment and cluster regions of the spoken captions which approximately correspond to words. Then, we exploit between-cluster similarities in the embedding space to associate English pseudo-word clusters with Hindi pseudo-word clusters, and show that many of these cluster pairings capture semantic translations between English and Hindi words. We present quantitative cross-lingual clustering results, as well as qualitative results in the form of a bilingual picture dictionary. Finally, we show the same analysis for a joint training using three languages at the same time, with Japanese as the third language."],"dc:description.degree":["M. Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/124231"],"dc:language.iso":["eng"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission."],"dc:rights.uri":["http://dspace.mit.edu/handle/1721.1/7582"],"dc:subject":["Electrical Engineering and Computer Science."],"dc:title":["Towards multilingual lexicon discovery from visually grounded speech"],"dc:type":["Thesis"],"thesis:degree_name":["Master"]},"updated_at":"2026-07-22T22:21:49Z"}