CrazyEngineers
  • Microsoft Speech Recognition Breakthrough - Close To Star Trek's Universal Translator?

    Ankita Katdare

    Administrator

    Updated: Oct 21, 2024
    Views: 862
    During a presentation, Microsoft's Chief Research Officer, Rick Rashid has showcased the company's breakthrough in speech recognition technology with a software that translates spoken English into spoken Chinese almost instantly! This translator is special because it tries to preserve the effectiveness of the speaker's voice, so when you hear the translated version, it still feels personal. How cool is that?
    They have minimized the error rate in translation from previous one word in 4 or 5 incorrect to now a word in 7 or 8.
    The translation from English into Chinese takes place in two steps - The first takes English words and finds the Chinese equivalents, and while non-trivial, this is the easy part. The second reorders the words to be appropriate for Chinese, an important step for correct translation between languages. Mr. Rashid delivered a dramatic presentation that converted his English to Chinese and it garnered the cheers from the crowd of 2000 mostly Chinese students
    In other words, we may not have to wait until the 22nd century for a usable equivalent of Star Trek’s universal translator!
    Check out the presentation -


    What do CEans have to say about this?
    0
    Replies
Howdy guest!
Dear guest, you must be logged-in to participate on CrazyEngineers. We would love to have you as a member of our community. Consider creating an account or login.
Replies
  • Kaustubh Katdare

    AdministratorNov 8, 2012

    This should have been developed on priority. But better late than never. The speech conversion is likely to solve the problems of communication between people. I'm quite sure the technology will finally make it to the mobiles in the form of apps. When you're talking to a Chinese person, all you'll have to do is just turn on the app and it will translate the conversation in real time for you. But as you can guess, it requires evolution of two technologies - first the voice / speech recognition (which is still a very complex task) and real time translation (another very challenging task).

    The problem of the speech recognition is made more complex because of the varying accents of people all over the world. But at least Microsoft's taken a step in the right direction.
    Are you sure? This action cannot be undone.
    Cancel
Home Channels Search Login Register