In speaker-adaptive HMM-based speech synthesis, there are a few speakers whose synthetic speech sounds worse than that of other speakers, despite having the same amount of adaptat...
Junichi Yamagishi, Oliver Watts, Simon King, Bela ...
PropBank has been widely used as training data for Semantic Role Labeling. However, because this training data is taken from the WSJ, the resulting machine learning models tend to...
Discussion of time in interactive computer music systems engineering has been largely limited to data acquisition rates and latency. Since music is an inherently time-based medium...
Software development organizations are beginning to recognize that measurement is a prerequisite for systematic process improvement, and have started to measure their products and...
Christopher M. Lott, Barbara Hoisl, H. Dieter Romb...
Parse-tree paths are commonly used to incorporate information from syntactic parses into NLP systems. These systems typically treat the paths as atomic (or nearly atomic) features...