We present a framework to extract the most important features (tree fragments) from a Tree Kernel (TK) space according to their importance in the target kernelbased machine, e.g. ...
While nonnegative matrix factorization (NMF) has successfully been applied for gain-robust multi-pitch detection, a method to track pitch values over time was not provided. We emb...
The goal of the work described here is to limit the computation needed in unit selection Viterbi search for text-to-speech synthesis. The broader goal is to improve speech quality...
We present an algorithm that learns invariant features from real data in an entirely unsupervised fashion. The principal benefit of our method is that it can be applied without hu...
[Extended Abstract] Ken Wakita Tokyo Institute of Technology 2-12-1 Ookayama, Meguro-ku Tokyo 152-8552, Japan wakita@is.titech.ac.jp Toshiyuki Tsurumi Tokyo Institute of Technolog...