Spectral voice conversion is usually performed using a single model selected in order to represent a tradeoff between goodness of fit and complexity. Recently, we proposed a new ...
We describe a new GMM-UBM speaker recognition system that uses standard cepstral features, but selects different frames of speech for different subsystems. Subsystems, or “const...
—Wireless mesh networks (WMNs) promise to extend high-speed wireless connectivity beyond what is possible with the current WiFi-based infrastructure. However, their unique archit...
A core ontology is a mid-level ontology which bridges the gap between an upper ontology and a domain ontology. Automatic Chinese core ontology construction can help quickly model ...
We present an effective method for automatically selecting the appropriate scale of shape features that are depicted when rendering a 3D mesh in the style of a line drawing. The m...
Alex Ni, Kyuman Jeong, Seungyong Lee, Lee Markosia...