ABSTRACT
Teaching speaking is integral to a language curriculum, as the ability to speak in a foreign language is arguably one of the most valuable learning outcomes for language learners. However, access to high-quality speaking instruction, especially in countries where English is a foreign language, is often limited. In addressing the challenge of improving speaking, research has been called for to support the development of automated learning tools that can serve as learning resources. Technological advances have increased the prospects for automated spoken language technology to provide immediate and individualized feedback that targets specific linguistic phenomena. The speech phenomenon measured by a selected feature should be understandable to the intended audience. However, the definitions of some features are more transparent than others. Feedback features were initially selected based on their anticipated usability and usefulness as the feedback using expert judgment.
