papers AI Learner
The Github is limit! Click to go to the new site.

Towards Visually Grounded Sub-Word Speech Unit Discovery

2019-02-21
David Harwath, James Glass

Abstract

In this paper, we investigate the manner in which interpretable sub-word speech units emerge within a convolutional neural network model trained to associate raw speech waveforms with semantically related natural image scenes. We show how diphone boundaries can be superficially extracted from the activation patterns of intermediate layers of the model, suggesting that the model may be leveraging these events for the purpose of word recognition. We present a series of experiments investigating the information encoded by these events.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.08213

PDF

http://arxiv.org/pdf/1902.08213


Similar Posts

Comments