We present a semi-supervised source separation methodology to denoise speech by modeling speech as one source and noise as the other source. We model speech using the recently pro...
Interest point detection in still images is a well-studied topic in computer vision. In the spatiotemporal domain, however, it is still unclear which features indicate useful inter...
Machine involvement has the potential to speed up language documentation. We assess this potential with timed annotation experiments that consider annotator expertise, example sel...
Despite a growing desire to create smart homes, we know little about how networked technologies interact with a house’s infrastructure. In this paper, we begin to close this gap ...
Marshini Chetty, Ja-Young Sung, Rebecca E. Grinter
—We describe the design of an autonomous agent that can teach itself how to translate from a foreign language, by first assembling its own training set, then using it to improve...