Speech recognition is a much-used technology we’re all familiar with, but do we take advantage of its full range of possibilities? Computers have long been able to comprehend what we say; nevertheless, do they also recognize who’s saying it? How can we utilize this technology? This is precisely the question we posed before seeking problems that can be solved with this technology. In most applications available today, speech recognition functions strictly as a means of issuing commands to a computer. But the device can also listen to users and actively provide them with support.
In many forms of group communication, certain individuals tend to monopolize the conversation, and there are those who behave reactively since the others are doing all the work anyway. So it’s often the case that participation in the conversation is distributed unequally. Since, especially in business settings, such conversational imbalance can lead to deficiencies and losses, we decided to design an app for meetings. After extensive planning, we developed a prototype that demonstrates how the app works. A video seemed to us to be the ideal means of convincing others of the value of our idea. In this way, the software’s features and advantages are easy to highlight.
The basic idea is that the app starts up and then listens in, whereby it notes not only what’s said but also who’s saying it. Thus, it registers conversational participation during a meeting and documents it afterwards in the form of comprehensive statistics. This creates awareness and fosters more effective conversations.
Timo Lins (born in 1997), Emil Bruckner (born in 1998) and Noel Kurtaran (born in 1996) are three creative individuals with big visions and goals. In the wake of academic career paths that could hardly have been more diverse, they first met up in 2012 at Vienna’s High School for Graphic Arts. They’ve already collaborated on several projects, one of which is teem.