We address the problem of learning the mapping between words and their possible pronunciations in terms of sub-word units. Most previous approaches have involved generative modeli...
We propose an aspect-model-based reference speaker weighting. The main idea of the approach is that the adapted model is a linear combination of a set of reference speakers like r...
Multiple-input multiple-output (MIMO) systems achieve significant diversity and array gains by using transmit beamforming. When complete channel state information (CSI) is not avai...
Application-specific system-on-chip platforms create the opportunity to customize the cache configuration for optimal performance with minimal chip estate. Simulation, in partic...
Mixture-of-Experts (MoE) systems solve intricate problems by combining results generated independently by multiple computational models (the “experts”). Given an instance of a...