The covariance matrix adaptation evolution strategy (CMAES) has proven to be a powerful method for reinforcement learning (RL). Recently, the CMA-ES has been augmented with an ada...
As robots and humans move towards sharing the same environment, the need for safety in robotic systems is of growing importance. Towards this goal of human-friendly robotics, a rob...
We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech,...
Igor Malioutov, Alex Park, Regina Barzilay, James ...
We provide two compressive sensing (CS) recovery algorithms based on iterative hard-thresholding. The algorithms, collectively dubbed as algebraic pursuits (ALPS), exploit the res...
Data imputation approaches for robust automatic speech recognition reconstruct noise corrupted spectral information by exploiting prior knowledge of the relationship between targe...