Inphodrive has launched a research program in cooperation with a team of Tel Aviv University and industrial rehabilitation specialists.
The researchers believe the real breakthrough in media technologies can be reached by exploring principally new media space, more specifically, a fully functional spoken Web browser.
The development of a voice-based browser -- operating in “voice cyberspace” -- represents a significant first step toward the development of a new human–machine interface (HMI). A voice user interface (VUI) will stand in contrast to today’s graphical user interface (GUI).
A real and effective VUI will be created through the analysis of a broad range of factors connected to HMI interactions, including psychological, cognitive, ergonomic, and others. To arrive at the VUI, researchers plan to analyze different aspects of textual structures, hypertext components, “audio images,” and navigation in a new, more intuitive hyperspace etc.
The potential envisioned extends well beyond simple vocalizing of textual information and voice commands as currently achieved in text-to-speech (TTS) and speech-to-text (STT). In fact, scientists could define a new type of virtual reality (cyberspace). Today’s cyberspace is based on visualized hypertext associated with additional visualized data row. It relies on the user’s ability to perceive a visual data row and then decode it. Modern network protocols and browsers help users surf, or navigate, in this virtual space. On the one hand, accessing this cyberspace basically requires sitting opposite a computer screen, making it then accessible to most users. Visually impaired people, however, have difficulty or are completely unable to access this visual cyberspace. By exploring a new audio cyberspace, more people will be able to effectively access useful information during driving, buying, and carrying out other activities that require visual attention. An effective VUI will open new horizons for people with vision and mobility problems.
The effectiveness of audio space perception will be high; in some cases even higher than that of visual space. The visual space today is crowded, jammed with a large number of ads and commercials. It decreases the effectiveness of accessing visual information and leads to lost time and user irritation.
When working within an audio space, the environment created is more trusting, almost filled with personal “features” and “personality.” Why? One reason is that audio cyberspace filters out much of the excessive information present in visual cyberspace.
The Inphodrive and Tel Aviv University teams hope that as result of their collaborative effort a truly new type of media product will be available for industrial and consumer applications. The first areas where the research results will be implemented are in the mobile workforce and for the visually impaired.