Learning digits via joint audio-visual representations

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.

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2017

Author dc:creator

• Kashyap, Karan

Advisor dc:contributor.advisor

• James Glass.

• Electrical Engineering and Computer Science.

Statement 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.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/113143

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/113143