Phonetic Coding of Kanji

Enhanced speech coding based on phonetic class segmentation

Given a baseline speech coder and speech with an available phonetic class segmentation, a number of potential enhancements to that coder become possible. While the quality of speech segmentation by phoneme and phonetic class is constantly improving, we use TIMIT to generate phonetic class segmentation as a basis for initial testing of these techniques. Using coders drawn from the MELP family, w...

Title A phonetic Vocoder for Very-Low-Rate Speech Coding

Systematization and improving efficiency in Kanji learning, based on quantitative analysis involving structural decomposition and coding

This study categorized problems in learning kanji encountered by Japanese language learners (non-kanji background) into three groups: (a) problems within the kanji itself, (b) problems in the teaching method, and (c) problems with language learners' attitude and approach to kanji study. This categorization was based on evidence from Japanese language learners' difficulties with kanji study, evi...

Rotated Kanji Character Recognition

We proposed a rotated character recognition method using eigen-subspace characterized multiple projection and simple projection. Then the multiple projections showed a higher accuracy at low dimensions than a simple projection for alphanumeric 62 categories. This time, we applied it for the first class of Japanese Industrial Standard (JIS) Kanji set which includes 2,965 categories. As the resul...

Augmented Reality Kanji Learning

ARToolKit programmers are familiar with the kanji symbols supplied with the distribution. Most of them have do not know what these kanji symbols mean. We propose a piece of educational software that uses collaborative Augmented Reality (AR) to teach users the meaning of kanji symbols. The application is laid out as a two player Augmented Reality computer game. The novelty of our approach is tha...