17 citations · 32 across the 18 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017
Learning Modality-Invariant Representations for Speech and Images
Kenneth Leidal, David Harwath, James Glass
In this paper, we explore the unsupervised learning of a semantic embedding space for co-occurring sensory inputs. Specifically, we focus on the task of learning a semantic vector…
cs.CL2017
Learning Word-Like Units from Joint Audio-Visual Analysis
David Harwath, James R. Glass
Given a collection of images and spoken audio captions, we present a method for discovering word-like acoustic units in the continuous speech signal and grounding them to semantica…