Dynamic noise adaptation (DNA) [1, 2] is a model-based technique for improving automatic speech recognition (ASR) performance in noise. DNA has shown promise on artificially mixe...
This paper introduces at robust interactive method for speech understatnding. The generatlized LR patrsing is enhanced ill this approach. Patrsing proceeds fl'om left to righ...
At the intersection of robotics, computational geometry, and manufacturingengineering, we have identifieda collection of research problems with near-term industrial applications. ...
Geographic face routing algorithms have been widely studied in the literature [1, 8, 13]. All face routing algorithms rely on two primitives: planarization and face traversal. The...
Young-Jin Kim, Ramesh Govindan, Brad Karp, Scott S...
We study unsupervised learning of occluding objects in images of visual scenes. The derived learning algorithm is based on a probabilistic generative model which parameterizes obj...