Slashdot Mirror

← Back to Stories (view on slashdot.org)

Baidu Releases Open Source Artificial Intelligence Code (thestack.com)

Posted by samzenpus on from the check-it-out dept.

An anonymous reader writes: Chinese web services company Baidu has released a new artificial intelligence software called WARP-CTC. The code is apparently capable of speech recognition, particularly for short segments, that exceeds human capability. The source code uses an approach called 'connectionist temporal classification' and has been released on GitHub.

2 of 34 comments (clear)

  1. "better than human" was achieved in 1994, already by ffkom · · Score: 5, Informative

    I've been developing automatic speech recognition systems in the 1990s. Back then, the best performing recognizers were based on Hidden Markov Models, and for "out of context" tasks like "determine whether an individual spoken word from an unknown speaker is 'nine' or 'none'", the automatic recognizers already achieved better recognition rates than humans. However, the specific human strength when recognizing fluent speech is to (a) quickly adapt to different speakers and (b) to fill in all the uncertain words from the understanding of the context, requiring "world knowledge". And that strength makes a very big difference. So the claim in the article is not really anything special, it is to be expected that computers are better than humans in this special task, for at least the last 20 years.

  2. You would be surprised how bad you are... by ffkom · · Score: 4, Informative
    ... understanding speech if you had somebody (not yourself, of course) make recordings of strangers on the street uttering just a single word, each, randomly picked from a dictionary book dictionary. Chances are your recognition rate would be somewhere around 90%.

    Automatic recognizers achieve better rates on this task - but they'll loose against you when it's complete, sensible sentences that are being spoken, even more so if you heard more sentences from the speaker, before.