METHOD OF LOCATION IDENTEFICATION BY VOICE NAVIGATION IN THE INDOOR SYSTEMS

Abstract

The article deals with tasks of indoor navigation with the usage of voice comands. To solvetasks of indoor navigation there are used different approaches, such as mapping the premises, determining the current position, determining the trajectory. With the rapid improvements in software and hardware, last years it's become more popular to use voice assistance. The implementation of voice navigation and speech recognition is a very complicated, time consuming and costly process. Usually existing on the market speech recognition systems are not properly documented, described, without possibility to integrate it with other software, limited in number of requests available for users, or paid. To formulate the requirements to suchsystems authors analyzed functionality of the most widely used voice assistants such as Google Assistant, Siri, Cortana. For indoor navigation systems existing solutions provide voice assistance for navigation within previously defined route. In the paper authors propose a method of determining a predetermined indoor location based on received voice commands, which uses fuzzy output to determine the position of the beacon according to the voice command. For voice recognition there were used hidden Markovs models. The developed method is used in BLE 4.0 based navigation systems and unlike existing ones, it allows user to use voice commands and fuzzy rules to find a specific location. Developed method was implemented in the Smart-Campus Mobile Application by developing the module of voice navigation, which enhances the ability to interact with the university's infrastructure and make it more inclusive for visitors, students and staff.