Learning digits via joint audio-visual representations
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017.
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2018
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/113143 |
| _version_ | 1811078134649323520 |
|---|---|
| author | Kashyap, Karan |
| author2 | James Glass. |
| author_facet | James Glass. Kashyap, Karan |
| author_sort | Kashyap, Karan |
| collection | MIT |
| description | Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2017. |
| first_indexed | 2024-09-23T10:54:05Z |
| format | Thesis |
| id | mit-1721.1/113143 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T10:54:05Z |
| publishDate | 2018 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1131432019-04-11T03:26:30Z Learning digits via joint audio-visual representations Kashyap, Karan James Glass. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. 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. 2018-01-12T20:59:23Z 2018-01-12T20:59:23Z 2017 2017 Thesis http://hdl.handle.net/1721.1/113143 1017990448 eng 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 60 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Kashyap, Karan Learning digits via joint audio-visual representations |
| title | Learning digits via joint audio-visual representations |
| title_full | Learning digits via joint audio-visual representations |
| title_fullStr | Learning digits via joint audio-visual representations |
| title_full_unstemmed | Learning digits via joint audio-visual representations |
| title_short | Learning digits via joint audio-visual representations |
| title_sort | learning digits via joint audio visual representations |
| topic | Electrical Engineering and Computer Science. |
| url | http://hdl.handle.net/1721.1/113143 |
| work_keys_str_mv | AT kashyapkaran learningdigitsviajointaudiovisualrepresentations |