Training speech through visual feedback patterns

The paper describes a new version of a visual feedback aid for speech training. The aid is a PC based speech processing system that visualizes incoming signal and its most relevant parameters (such as volume, pitch, timing, spectrum) and compares them to utterances recorded by reference speakers. The goal is to help a trained person in identifying the most severe deviations in his or her pronunciation. The learning through visual comparison is supported by displaying multiple reference utterances, including phonetic labels both to the reference speakers’ and trainee’s speech, indicating the areas with larger deviations in any of the displayed features and offering a simple tutoring assessment of the trainee’s attempts. Primarily, the system was aimed at hearing-impaired users, but its features make it well applicable also for foreign language pronunciation learning and practicing. The latter possibility was verified in an experiment in which a group of subjects tried to learn pronunciation of a couple of words in an exotic for them foreign language.