Saber-Tooth Squirrels Required

by Translation Guy on November 8, 2012

On the treadmill with voice recognition and machine translation.

NTT Docomo, Japan’s leading cell phone carrier, has unveiled its real-time speech-to-speech translation service, reports As a supplier of telephone interpreters, I’ve been waiting for this for a long time, since I used to imagine it would put us all out of work. But I’ll hold off on searching Craigslist for a new job just yet. Fact is these tools are just window dressing, press release fodder for the uninitiated, because they just don’t work that well. I haven’t tested the DoCoMo tool, but I’m sure it’s the same old tech BS.

How do I know? Because I’m using the best speech recognition tool available to compose this post. That’s right, no more typing for me. It’s all voice recognition for TranslationGuy.

Tendinitis has ended my typing days. I’m using Dragon Naturally Speaking 12, the latest and greatest voice recognition tool from Nuance. It is an amazingly powerful technology, a real game-changer. I’m writing twice as fast, with half the pain, after only a few weeks of intensive frustration. Thinking before speaking does not come naturally to me.

Nuance technical support tells me that the tool will never be able to transcribe the name of 1-800-Translate because of the unfortunate use of hyphens in our brand. And to Dragon’s tin ear,“Ken” remains indistinguishable from “10” or “can,” no matter how many times I program the tool. Unless I change brand and name (any suggestions welcome) a careful post-edit is always required.

Which reveals the big dirty secret behind Apple’s OS, and it’s not that the maps are stupid, which I guess is not really a secret. The secret is  that Siri sucks. Apple’s voice-recognition tool is powered by the same Nuance engine I am struggling to train right now. Having spent hours training it to my voice, and edited at my hand, it is an amazing tool, but when applied to real-time communication the error rate is too high. Siri may be geek-sexy, but her output does not put out.

This is great for my business, because it means our telephone interpreters are going to be around for a long time. We still turn the wheels of real-time translation, just as Fred Flintstone’s saber-tooth squirrels on their treadmills kept Stone-Age Bedrock rolling. Yabba dabba doo!

Without training first and post-edit last, voice recognition and machine translation are just useful-ish. Combining two halves of two incomplete processes just doubles your troubles. But once we  get some saber–toothed linguists into the automation dust-up, wonders can be achieved.

If I could, I’d make everyone on my team use them all the time. The training would be killer, but the payoff is we would all make a lot more money, at least until the other guys figured it out.

Mastering these automation processes requires patience, persistence and practice (one of my Dad’s favorite lines, although I think he was mostly referring to sex whenever he said it). To make good use of these tools requires planning and changes to old habits of work and thought. The only thing more painful is carpal tunnel syndrome, or business lost to tech-savvy competitors, which is even more painful to my wallet. Ouch!


  1. Wilber says:

    I know several translators who dictate to Dragon and praise it to the skies. For words etc that Dragon can’t handle, they just type such items themselves as they go, since they’re sitting at the keyboard anyway. It works very well for them.

    I couldn’t do that (old dog new tricks you know). I lean back in a recliner and dictate everything to a human transcriber (HT) who’s 99.99 percent accurate. Then I edit the raw stuff onscreen after the HT transmits it back to me. A bit of cost but it greatly boosts productivity without the frustration of training dumb machinery, and it’s physically easier along with other benefits.

    Some years ago I was a “guinea pig” post-editor of MT output. It was bad but some fans of it say vast improvements have been made since then.

  2. I honestly don’t think Siri is that much of a game changer, sure I used it a lot when she/it first came out, but after too many errors I just reverted to manually doing things. I think voice recognition software is a great thing, but truly effective stuff that can handle all the nuances of real world speech is still a ways away.

  3. Eugenie says:

    I have not heard the Flintstones theme in years, surprised myself by remembering the words when I can’t remember what I ate for lunch yesterday.

    • Ken says:

      Could it have been a brontosaurus burger?

  4. I think the really revolutionary part about the DoCoMo app is the ability to differentiate between accent like British, American or Australian English. Not perfectly mind you, but an importnt step, it is only version 1.0.

  5. Would you honestly recommend Dragon? I’ve been thinking of incorporating a voice recognition tool into my work and is that the best there is, or will there be something better on the market soon that I should ait for?

  6. the robots haven’t quite taken over yet, I have used the stuff before, and honestly I think I’m still more productve the old fashioned way (although typing on a laptop is hardly old fashioned), I have to deal with less errors and editing.

  7. Lana Chin says:

    Siri does suck, Apple has been less and less impressive with each product release. I’ve never trusted voice recognition stuff, but I’ve always typed insanely fast, so I’ve never felt the need to explore it in depth.

  8. I use seech recognition software too, but do you ever feel weird sitting there talking to your computer or is that just me?

    • Ken says:

      No, that’s just you. At least you’re the only one to mention it so far.

  9. I’ve played around with voice recogition stuff on various platforms, for various purposes ovr the years. The consistent thing I’ve found is the mass amount of errors with even the most simplistic stuff and even with training it to your voice, I’m holding off for another year or two, by then I think that something servicable for real day to day life will emerge.

  10. I had thought of investing in something like Dragon, as I spend a fair amount of my time doing data entry, but the fact hyphens prove problematic throws a kink in that plan as the filing system I use is hyphen heavy.

  11. It’s going to happen one day, the Star Trek universal translator isn’t that far away, technology grows exponentially.

LiveZilla Live Chat Software