Abstract-- Traditional methods of spoken utterance classification (SUC) adopt two independently trained phases. In the first phase, an automatic speech recognition (ASR) module ret...
Sibel Yaman, Li Deng, Dong Yu, Ye-Yi Wang, Alex Ac...
Abstract--A new grid conversion method is proposed to resample between two 2-D periodic lattices with the same sampling density. The main feature of our approach is the symmetric r...
Laurent Condat, Dimitri Van De Ville, Brigitte For...
Abstract-- A major drawback of artificial neural networks (ANNs) is their black-box character. This is especially true for recurrent neural networks (RNNs) because of their intrica...
Abstract-- Computing constrained shortest paths is fundamental to some important network functions such as QoS routing, which is to find the cheapest path that satisfies certain co...
Abstract-- This paper addresses preamble-based low complexity synchronization, channel estimation and equalization for Zero-padded (ZP) MB-OFDM based UWB systems. The proposed sync...