Numerous pilot programs that utilizes speech recognition technology to perform real-time language translations have been kicking around for years now, but Microsoft took the concept to a new level at its TechFest 2012 event last week.
Researchers at Microsoft have made software that would not just stop at translating what you have typed into another language. Also, the system could be used to make language tutoring software more personal, or to make tools for travelers.
In a demonstration at Microsoft’s Redmond, Washington, campus last week, Microsoft research scientist Frank Soong showcased how his software could read out text in Spanish using the voice of his boss, Rick Rashid, who leads Microsoft’s research efforts. In a second demonstration, Soong used his software to grant Craig Mundie, Microsoft’s chief research and strategy officer, the ability to speak Mandarin.
On the other hand, in English, an artificial version of Mundie’s voice welcomed the audience to an open day organized by Microsoft Research, concluding, “With the help of this system, now I can speak Mandarin.” The phrase was repeated in Mandarin Chinese, in what was still recognizably Mundie’s voice.
“We will be able to do quite a few scenario applications,” said Soong, who developed the system with colleagues at Microsoft Research Asia, the company’s second largest research lab, in Beijing, China.
“For a monolingual speaker touring in a foreign country, we will do speech recognition followed by translation, followed by the final text to speech output [in] a different language, but still in his own voice,” said Soong.
Similar to other off-the-shelf translators, the software created by Microsoft Research enables you to talk to it in your native language and send it out the speaker of a device as another language — Spanish, French, Chinese, or such. The program can currently translate between 26 difference languages including all the major languages of the world.
Moreover, Microsoft asserts that the program only needs an hour of training before it gets good enough to do live translation for you, and most of that is mastering the nuances in your voice.
The program works by using speech recognition, followed by translation, followed by the final text to speech output in a different language — while retaining the user’s original voice. Besides, the software will create a 3D image of your head that makes it look as if you are speaking the translation.
The technology has been formulated to make language tutoring software more personal, or to make tools for travelers. However, it merely takes about an hour of training to work — a pretty short time compared to the hours that would be required to learn a new language.
Microsoft’s vision in the translation sphere is broader than what has been produced by its rivals. It wants to use true-to-life virtual avatars that not only mimic your looks but also your voice and the movements of your lips when you speak.
Nevertheless, an excellent tool for people who travel to many different countries, and do not have the time to spend learning how to talk to the locals. The results produced from that vision can be impressive, but they can be creepy, too.