Abstract:

With the spread of mobile devices comes the possibility of using (relatively) cheap, wireless hardware embedded with plenty of sensors to perform real time Digital Signal Processing on live artistic performances. The Android Operating System represents a milestone for mobile devices due to its lightweight Java Virtual Machine and API that makes it easier to develop applications that run on any (supported) device. With an appropriate DSP model implementation, it is possible to use the values of sensors as input for algorithms that can modify streams of audio to generate rich output signals. Because of memory, CPU and battery limitations, it is interesting to study the performance of each device under real time DSP conditions, and also provide feedback about resources consumption to provide the basis for (user or automated) decision making regarding devices' use. This work presents an object oriented model for performing DSP on Android devices and focus on measuring the time taken to perform common DSP tasks as read from the input, write to output, and carry the desired signal manipulation. We obtain statistics regarding one specific combination of device model and operating system version, but our approach can be used on any Android device to provide the user with important information that can aid aesthetic and algorithmic decisions.