2026-09-18T19:28:52Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1131432026-06-06T00:49:35Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
James Glass.
Kashyap, Karan
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2018-01-12T20:59:23Z
2018-01-12T20:59:23Z
2017
2017
http://hdl.handle.net/1721.1/113143
1017990448
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 59-60).
Our goal is to explore models for language learning in the manner that humans learn languages as children. Namely, children do not have intermediary text transcriptions in correlating visual and audio inputs from the environment; rather, they directly make connections between what they see and what they hear, sometimes even across languages! In this thesis, we present weakly-supervised models for learning representations of numerical digits between two modalities: speech and images. We experiment with architectures of convolutional neural networks taking in spoken utterances of numerical digits and images of handwritten digits as inputs. In nearly all cases we randomly initialize network weights (without pre-training) and evaluate the model's ability to return a matching image for a spoken input or to identify the number of overlapping digits between an utterance and an image. We also provide some visuals as evidence that our models are truly learning correspondences between the two modalities.
by Karan Kashyap.
M.Eng.
60 pages
eng
Massachusetts Institute of Technology
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.
http://dspace.mit.edu/handle/1721.1/7582
Electrical Engineering and Computer Science.
Learning digits via joint audio-visual representations
Thesis
application/pdf
false
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="51a277fb-bbe2-4edb-83c2-9625ea9d9da3">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Language>eng</Language>
<Title>Learning digits via joint audio-visual representations</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2017</PublicationDate>
<Authors>
<Author>
<DisplayName>Kashyap, Karan</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://dspace.mit.edu/handle/1721.1/7582</License>
<Keyword>Electrical Engineering and Computer Science.</Keyword>
<Abstract>Our goal is to explore models for language learning in the manner that humans learn languages as children. Namely, children do not have intermediary text transcriptions in correlating visual and audio inputs from the environment; rather, they directly make connections between what they see and what they hear, sometimes even across languages! In this thesis, we present weakly-supervised models for learning representations of numerical digits between two modalities: speech and images. We experiment with architectures of convolutional neural networks taking in spoken utterances of numerical digits and images of handwritten digits as inputs. In nearly all cases we randomly initialize network weights (without pre-training) and evaluate the model's ability to return a matching image for a spoken input or to identify the number of overlapping digits between an utterance and an image. We also provide some visuals as evidence that our models are truly learning correspondences between the two modalities.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>