Slashdot Mirror

← Back to Stories (view on slashdot.org)

Rest In Peas — the Death of Speech Recognition

Posted by Soulskill on from the yale-in-ox-boom-i-crows-off dept.

An anonymous reader writes "Speech recognition accuracy flatlined years ago. It works great for small vocabularies on your cell phone, but basically, computers still can't understand language. Prospects for AI are dimmed, and we seem to need AI for computers to make progress in this area. Time to rewrite the story of the future. From the article: 'The language universe is large, Google's trillion words a mere scrawl on its surface. One estimate puts the number of possible sentences at 10^570. Through constant talking and writing, more of the possibilities of language enter into our possession. But plenty of unanticipated combinations remain, which force speech recognizers into risky guesses. Even where data are lush, picking what's most likely can be a mistake because meaning often pools in a key word or two. Recognition systems, by going with the "best" bet, are prone to interpret the meaning-rich terms as more common but similar-sounding words, draining sense from the sentence.'"

4 of 342 comments (clear)

  1. Buffalo buffalo by Anonymous Coward · · Score: 5, Insightful

    Buffalo buffalo Buffalo buffalo buffalo, buffalo Buffalo buffalo.

    1. Re:Buffalo buffalo by JanneM · · Score: 5, Insightful

      Most people won't be able to parse the sentence, though. I know I can't. I have no idea how to interpret it as anything but a string of nouns. My guess is, even fewer would be able to parse it if spoken (the capitals and the comma are, I assume, important hints). It'd be unrealistic and unproductive to require speech systems to actually do better than most humans on the task; if many of us can't parse the sentence then why expect a computer to do so?

      Better overall benchmark: require it to have the ability of a competent but not perfect second-language user. We're long used to dealing with that level of proficiency, whether because the conversant is a foreigner, a child, or has a dialect very different from our own.

      --
      Trust the Computer. The Computer is your friend.
  2. AI by ShadowRangerRIT · · Score: 5, Insightful

    Natural language processing *is* AI. And high accuracy speech recognition requires natural language processing if we expect to have accuracy rates approaching that of a human. Humans hear words partially or incorrectly all the time. We fill in the gaps from context, and we correct if the course of the conversation reveals that the original interpretation is wrong. Expecting computers to do better, when half the time the problem is the speaker, not the listener, means you need it to be able to make the same corrections from limited information on the fly, and after the fact that a human brain makes.

    --
    $_ = "wftedskaebjgdpjgidbsmnjgcdwatb"; tr/a-z/oh, turtleneck Phrase Jar!/; print
  3. Shout-outs to two idiots by Foobar_ · · Score: 5, Insightful

    This blog post is retarded. The author is correlating a drop in internet news articles about Dragon NaturallySpeaking with a flatlining of speech recognition accuracy rate.

    The Slashdot editor Soulskill is retarded for both not realizing this and for not reading the anonymously-submitted blog post (hmm no way it could have been the author) before approving it for the Slashdot front page. The guy is just out for more traffic to his rather pointless tech news commentary blog.

    Decline of Slashdot, internet signal-to-noise ratio, get off my lawn, etc.