Kenji Nagamatsu

Learn More
In this paper we propose two methods in order to implement unit selection-based text-to-speech engine into resource-limited embedded systems. While we have achieved improving the quality of synthesized speech by unit selection-based text-to-speech technology, there is a practical problem regarding the trade-off between the size of database and the quality(More)
We describe a corpus-based approach to improving synthesized speech quality and present two useful cost functions for unit selection. One is pitch-synchronous cross correlation for concatenation costs to reduce the noise caused by phase mismatch at concatenation points. The other is a discontinuous cost function for internal and concatenation costs to(More)
This paper. proposes a similarity measure which takes account of point-of-views (abbreviated to POV, hereafter) in the calculation of similarity values. So far many researches on similarity measures have been performed but none takes account of POVs. The similarity measure proposed in this paper is based on co-occurrence probabilities of words and this(More)
Finding an optimal path for a redundant robotic system to visit a sequence of several goal placements poses two technical challenges. First, while searching for an optimal sequence, infinitely many feasible configurations can be used to reach each goal placement. Second, obstacle avoidance has to be considered while optimizing the path from one goal(More)
—In this paper, a pre-identification method for Chinese named entity recognition is proposed. Internal information of entity name like family name, first name in person name, feature word in place name and organization name do not needed. Through entity name guessing based on context keywords, pre-identification is realized. Definition of bidirectional(More)
  • 1