This paper describes an adapatation of the tf-idf model to Japanese graphemephoneme alignment, without reliance on training data. The tf-idf model is optionally complemented with affixation and conjugation handling modules, and determines frequencies through analysis of “alignment potential”. The proposed system achieved a maximum accuracy of 94.74% on evaluation.

There is a current debate over the possibility and validity of synesthesia training experiments (Deroy and Spence, 2013; Rothen and Meier, 2014). In order to test whether a trainee should be considered to have acquired a trained form of synesthesia, a precise definition and specific diagnostic criteria of synesthesia are necessary. There is currently not one specific checklist available includi...

A Self-Learning system for Grapheme to Phoneme conversion is described and tested. The system acquires the knowledge needed for grapheme-to-phoneme conversion from a training session in which a large number of pairs of grapheme strings and their corresponding (manually verified) phonemic transcription strings are presented to the system. The result from the training is a stochastic decision tre...

Sixteen adult subjects were served in an experiment in which the writing of six unfamiliar graphemes was practiced. To investigate the learning process, we analyzed the absolute and relative changes of movement time of the first three consecutive segments as a function of practice. The results showed that movement time of all three segments decreased. This decrease was significantly less in the...