The OS X speech-to-text myth

There is a widespread myth in the Mac community that Mac OS (yes, not just OS X) has included “speech recognition” for many years. I would argue that through well-publicised Jobs keynotes, in-store lecture theatres, many fansites with documentation, mostly in the form of two-paragraph “tips”, and, more recently, instructional videos on the Apple website, user knowledge of OS X is much better than user knowledge among Windows users. How is it, then, that very few Mac users actually use “speech recognition” (my claim)?

You will find that historically, speech recognition has been synonymous with “speech to text” (which the Wikipedia article still redirects from: speech to text). During the sometimes claimed twenty years that OS X has included “speech recognition”, third party applications such as iListen and ViaVoice for Mac have continued to sell. So is this an anomaly of history, where Mac customers have for years continued to buy third party software for functionality that was actually included in their OS out of the box? No, something perhaps more perfidious. There has been a semantic shift, where “speech recognition” for Mac users has become identical with “Speakable items“, a feature of Mac OS introduced as part of the OS in March 1994, although available from 1993 as a stand-alone program called PlainTalk. Speakable items includes phrases that allow you to navigate windows and certain programs; it also lets you define your own phrases which you can associate, for instance, with Automator scripts. I’ll reiterate again: PlainTalk and Speakable Items are not speech recognition! At best, it might be called phrase recognition, and its 1993 release date is very little to show for “20 years of history”.

Finally, as of this writing, speech to text in Tiger can neither be found in the System Settings, nor in the Services menu. Since it hasn’t been mentioned in any of the keynotes preceding Leopard, I doubt it will suddenly appear. (Remember the “top secret features”? Where are they?) If you wish to prove me wrong and demonstrate that scores of Mac users have been morons to buy third party software that did real speech recognition, and that purported experts have been ignorant, please post a reply!

That failing, I have to conclude that a certain gadget website (to be punished with a non-link) has been quite unfair in its recent comparison of Mac OS X 10.5 and Windows Vista, which ignores Vista’s true speech recognition.

8 thoughts on “The OS X speech-to-text myth

  1. Pingback: Rob's Rhapsody : Comparing Speech Recognition in Vista vs Apple OS X

  2. The major issue I have with speech to text on almost any platform I tried is the fact that this technology is almost useless if there is any background noise or even at times if your head is moving away from the microphone.

  3. The text to speech ans speech to text angines are not “there” yet. When the neural networks algorithms were in their prime, not transcending the status of a buzz-word several attempts were made to solve these problems.
    This reminds me of the translators when translating from english to russian and back to english “The flesh is weak, but the Spirit is strong.”, it came back as “The body is weak but the vodka is strong.”

    Nice post!

  4. Sadly, because I REALLY need to be able to dictate, rather than type, for producing long text documents I have to use my Windows PC to do this. This dictation functionality was included in Microsoft Office (for Windows) since 2002. It’s no longer included in Office 2007 (except for Excel), however, it is now a part of Vista and therefore the speech to text functionality can be used across a variety of programs, like Office2007. I’d much rather use my Mac for everything, but so be it, on my Windows machine I can do dictation without buying additional software. To give Windows their due, their speech recognition for dictation works really REALLY well and their version of “speakable items” is very robust and frankly better than Apple’s. I love my Mac, but Apple has really dropped the ball by not including speech to text. Many people want this technology and for people who are disabled, this functionality is essential. It pains me to say it but, thanks Microsoft!

  5. Yup, the Mac speech thingy is not true speech recognition, but that is the last on the list of things great about OSX. It’s great for home users and computer professionals alike. To have a unix OS under the hood is key. I have healed a number of windows users and they all have thanked me over and over again. The Mac commercials are so incredibly on the mark. When I meet a Windows enthusiast they are truly “a PC”, usually. So throw Vista out the window, go by some new clothes, do some art, and be “a Mac”. Back on the subject: MacSpeech is the commercial ware, that uses the Dragon engine, for OSX.

  6. A few points of moderation there, if I may, and an attempt to stick to topic. Now, speech recognition *is* included with Vista out of the box (someone will point out that it’s probably not included in all of the differently priced editions, but I’ll let that slip, just once). With the Mac, even though it’s difficult to say how much you’re paying for the OS since it comes bundled, you have to pay extra. As far as I’m concerned, consumer speech recognition wasn’t really working until Dragon Naturally Speaking (DNS) version 9 and Windows Vista. You mention MacSpeech, but that’s only recently been given a license for the DNS engine (I seem to remember that it was supposed to be included in iListen 3.0, but they seem to have changed the name of their product to “Dictate”). So why is Apple Inc. sitting on its hands? Based on their history, they should have been the ones to come up with this missing piece of “multimedia”. Microsoft may have lost the plot on a grander scale with Vista, but Apple nearly missed the plot with speech recognition. But yes, Speakable Items are quite good for what they are, sort of an Apple Remote 1.0 really.

  7. I love macs and indeed osx, but having just tried the speech recognition it is utterly useless. I’d have more chance training a dog to understand what I’m saying… just poor!

  8. Is there any good software (or a commination > like Office/Mac & a speech recognition) that works with Mac OS X where I can truly dictate my document with minimal corrections or typing? I really need to be able to dictate, rather than type, for producing a text document in a reasonable amount of time.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s