VOICE NAVIGATION: TECHNOLOGY AND APPLICATIONS

The goal is to get more navigable sites anywhere and anytime. Technological evolution advances to integrate the internet in any type of device, transforming and progressively improving user navigation. From this premise are born new forms of accessibility and interaction such as voice navigation. Protagonist of today’s article.

Let’s start with what classic navigation on mobile devices offers. We enter the website of a theater, for example. We sailed a little until we found the work we would like to see, we selected the day and time of the performance and, finally, before moving to the pay catwalk, we selected the seats from a seating map. So with many other transactions like booking a hotel night, a plane ticket or tickets for a concert. And the question arises: Could we not do this whole process by voice? Everything would be easier, accessible and would greatly improve the user experience when browsing websites. If Siri and Cortana already allow us to navigate our devices, mobile or desktop, surely technologically it is feasible. The answer is Yes, all this is possible thanks to voice navigation.

Technology behind the voice navigation

Using oral language, voice navigation allows you to use an online function or application. There are many tools that have appeared to integrate voice navigation technology on the web. For example, from the W3C, international consortium that generates recommendations and standards to ensure the long-term growth of the World Wide Web, propose VoiceXML. In order not to get into too technical subjects, it is a standard XML format that allows you to design interactive voice dialogues between a person and the computer with which you are interacting. For example, while HTML templates are interpreted by a visual browser, VoiceXML documents are interpreted by a voice browser. This tool together with other languages make up the Speech Interface Framwork, a platform focused on improving features such as speech synthesis or voice recognition. This can result in the generation of oral dialogues between humans and computers or the interpretation of grammar and semantics. From Emexs we have chosen to use the Google API (Google Cloud Speech API) when optimizing critical data entry processes. This tool allows developers and engineers to convert audio into text using powerful neural network models. With the use of Google Cloud Speech API we intend to improve usability to allow to finish procedures in optimal times without involving excessive bounce. In this way and, especially in small devices, we could have a model of navigation "on demand". Another advantage of this API is that it has more than 80 languages with simultaneous translation. An addition of the most interesting considering that nowadays the websites are increasingly multi-language.

Possible applications of Internet voice navigation

Apart from the above, such applications could help improve the internet accessibility of groups such as the blind. And not only this, for people with psychomotor problems who cannot use a keyboard and a mouse would be a great quality jump in their navigation. All indications are that voice navigation applications will grow in parallel with the reduction in device ratios. Especially keyboards that become less and less practical. Listing voice navigation applications would be as simple as letting your imagination run wild. Can you think of any?