Tomoki Hamagami

Learn More
This report describes a method for estimating the separation degree at the bunsetsu boundary (SD) for Japanese text-to-speech synthesis. Our method gives us the prosodic symbol without using complicated linguistic analysis. First we classify bunsetsus according to the nal morpheme. Each classied bunsetsu has a temporary separation degree in advance. We call(More)
This report proposes a simple and practical model for generating relatively monotonous, but suciently natural, prosodic features by analyzing restricted natural speech. The basic assumption of this model is that the natural F0 pattern can be obtained without complicated linguistic analysis. To achieve this prosodic control, we have analyzed and modeled this(More)
A new diploid genetic algorithm (DipGA) with network structure which enables autonomous adaptation to dynamic environment is proposed in this paper. The proposed algorithm has the network weights changed adaptively according to the pattern of dynamics in the environment during the evolving loop. The state of the art of the algorithm is that the genotypes of(More)