Design and Development of Speech Interaction: A Methodology

Using speech in computer interaction is advantageous in many situation and more natural for the user. However, development of speech enabled applications presents, in general, a big challenge when designing the application, regarding the implementation of speech modalities and what the speech recognizer will understand. In this paper we present the context of our work, describe the major challenges involved in using speech modalities, summarize our approach to speech interaction design and share experiences regarding our applications, their architecture and gathered insights. In our approach we use a multimodal framework, responsible for the communication between modalities, and a generic speech modality allowing developers to quickly implement new speech enabled applications. As part of our methodology, in order to inform development, we consider two different applications, one targeting smartphones and the other tablets or home computers. These adopt a multimodal architecture and provide different scenarios for testing the proposed speech modality.