Mitsuo Komura

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)
We propose a new neural network model and its learning algorithm. The proposed neural network consists of four layers-input, hidden, output and final output layers. The hidden and output layers are multiple. Using the proposed SICL(Spread Pattern Information and Cooperative Learning) algorithm, it is possible to learn analog data accurately and to obtain(More)
  • 1