Speech Recognition-Based Mobile Geo-Mashup Application Technology

In this paper, we propose and implement speech recognition-based mobile geo-mashup application technology. The conventional HCI-method for mobile-based geo-mashup generally uses a detachable stylus-based touch screen or key-pad. However, interaction mechanisms of the mobile devices cannot utilize all or any of their visual resources, since the activities of users are dynamic and the mobile devices have limited resource and a small touch screen. In contrast, this technology maps and displays geographical information of the relevant country, referring to 70 country names that are recognized by the embedded Vocabulary-Independent Speech Recognizer (VISR), on the mobile mixed Web-map module. This issue may enable more convenient and powerful UI (User Interface) in the mobile-based geo-mashup domain for geographical distribution of various mobile-content selected from all the world´s nations.