Abstract:

Computer technologies are everywhere around us, and learners will become more and more dependent from technology advances in the future. Qualitative and effective training of the people remains one of the most important tasks of our time. A wide variety of software tools and web services are designed and developed for educational purposes. New direction of the development of such kind of software is to enforce usage of synthesized audio lectures in order to accelerate learning, and diverse perception from written lectures in different form of audio speech. Desired functionality of such software systems includes, but is not limited to: ease of generation, management, and sharing of lectures in audio format. Current paper describes software architecture of the prototype, based on REST client-server application. There are defined workspaces for audio lectures management and grouping with specific file structure. Vocabulary structure is used to define and redefine words, numbers, and phrases to improve quality of the generated speech especially for either domain-specific terms or localization of pronunciation of the person names.

Keywords:

text-to-speech, REST services, speech generation, e-learning.