Since 1990, research began on systems controlled by voice commands. In recent years, systems with useful and commercially viable applications for developers and consumers have been known.
By Richard Santa
In this increasingly convulsed world, in which time is not enough and people seek to perform several activities at once, the trend in technological developments is to make everyone's life easier. That's why manufacturers are now targeting equipment and systems that can be controlled by voice.
Google is one of the main drivers of this technology. At its most recent Developer Conference in May, it presented the voice recognition system for the search engine, through which it allows you to ask questions and get the answers spoken.
This new search system requires the use of the Google Chrome browser version 27 or higher for its operation and authorization so that the program can use the computer's microphone.
And although this has been a novelty, the criticism has not been lacking. One is because of the language, because it's only available for English, no matter which language is the default in the Google account. Another problem reported is that many times when trying to use it there is an error on the page, but the company's executives have indicated that it is due to the excess use of the platform in its early days.
One of the most anticipated announcements of Google I/O 2013 by tech junkies was the details of Google Glass. It was known that these also include a voice command to execute actions such as taking photos, locating on maps or using the internet.
Another of the tech giant's apps that also uses voice commands is Google Now, a smart personal assistant available for the Android and iOS operating system, which uses a natural language user interface to answer questions, make recommendations, and act by delegating requests to a suite of web services.
Google's three products with features through voice commands share the same difficulty, currently only working with the English language, and those with Spanish options, such as Google Now, have problems with language recognition. But this language restriction will most likely be overcome in the coming months.
Not the only one
Google isn't the only tech developer working on voice commands. The company NEC recently reported that its researchers are currently developing a voice control system for smartphones that will overcome one of the main problems that these systems have, ambient noise.
NEC found a solution to situations with intense noise that did not allow the use of voice commands. Its system will work through two microphones, one will pick up the ambient noise and the other exclusively the different types of voice. This avoids having to get too close to the microphone to the mouth so that the device can work well.
In the same sense works Sherpa, a virtual assistant that allows you to execute and schedule tasks through voice commands. This Spanish development has been very well received because its native language is Spanish. In its first six months it reached half a million downloads.
Experts have pointed out that it is a better version than Google Now for its handling of the Spanish language. Therefore, its creators decided to take advantage of this success and are currently working on the application that will allow them to have a presence in Google Glass.
For its part, Apple has not been left behind and during 2011 launched its iPhone 4S phone with the Siri application, which uses natural language processing to answer questions, make recommendations and perform actions by delegating requests to a set of web services that is increasing. One of its advantages is that it adapts to the user's individual preferences over time and personalizes the results, as well as performing tasks such as booking a table for dinner or ordering a taxi.
Other applications
Voice commands have benefited from the rise of mobile devices, because most applications are aimed at these devices. But they are not the only ones. As we saw earlier, voice applications for Google can already be used in your search engine from any device or computer.
Also, the system in which NEC works aims to be useful for other industries, such as factories or stores, which may benefit from the operation of machines by voice allowing employees to perform other activities at the same time using their hands.
Windows 7 also brought voice commands for the first time for some of its applications, such as managing music after system setup and recording the commands to be used. Even game consoles, such as the Xbox 360, today have this type of service.
Some of the most benefited from voice commands have been people who have some type of disability, who have found solutions to facilitate accessibility, especially when they have motor or mobility difficulties.
Types and uses
In general, voice commands seek to allow communication between humans and machines, but some theorists say the main challenges of these systems are in the forms of language (phonetics, semantics, accent, among others) to have an acceptance of the correct message and an adequate response.
Currently voice command solutions are classified into several options. For example, if it requires prior training before starting to be used, or if it is accessible to anyone or is only able to recognize only one user.
It must also be differentiated if the system allows the user to speak in a row or must pronounce word for word, giving a short space of time between each one to facilitate recognition. And a fundamental factor is to be clear about what are the functions that the system recognizes, if it has some predetermined phrases or an extensive language.
Although many see in voice commands solutions to everyday problems and even making life easier in common actions, it is clear that this is a technology in the process of research and development to achieve optimal functionality. A particular case would be that of drivers.
Many have talked about how useful voice commands can be for people when they're behind the wheel. But there are academic studies that have drawn attention to the risk these could bring to drivers. The Texas Transportation Institute, a department of A&M University, said in recent research that these functions could be more dangerous than chatting when behind the wheel.
They point out that these systems require much more attention, because in most cases the order given to the device must be corrected, which reduces the driver's reaction time to an unforeseen event on the road. This would be one more problem that adds to the conflict that has to combine the steering wheel with mobile devices.
But at the pace that research is advancing today and with the interest of so many companies to develop their applications, it is possible that in a couple of years its functionality will be greater, above all, solving problems such as the distortion that ambient sound can generate, the uses in different languages, the recognition of the different characteristics of the speaker and even the distractions for drivers.
