Forgot your password?
typodupeerror
Input Devices Software Apple

Mac Version of NaturallySpeaking Launched 176

Posted by kdawson
from the listen-what-i-say dept.
WirePosted writes "MacSpeech, the leading supplier of speech recognition software for the Mac, has canned its long-running iListen product and has launched a Mac version of Dragon NaturallySpeaking, the top-selling Windows speech recognition product. MacSpeech had made a licensing agreement with Dragon's developer, Nuance Communications. The new product is said to reach 99% accuracy after 5 minutes of training."
This discussion has been archived. No new comments can be posted.

Mac Version of NaturallySpeaking Launched

Comments Filter:
  • Talking to oneself (Score:5, Informative)

    by flyingfsck (986395) on Wednesday January 16, 2008 @04:14AM (#22063844)
    I tried Dragon a number of times, but it feels too much like talking to oneself. Training it is a chore too. 99% accuracy after 5 minutes is probably true, but I type much better than that. I suppose it will be great for people who either can't type properly or are lysdexic.
  • Isn't that... (Score:2, Informative)

    by Sylos (1073710) on Wednesday January 16, 2008 @04:17AM (#22063868)
    the whole intention of Dragon? For those people who *are* impaired in some way or another? I mean...I could never "speak" out a paper or something. I'd end up tearing my vocal cords out.
  • by Caspian (99221) on Wednesday January 16, 2008 @06:50AM (#22064614)
    I've worked with Nuance's server product in the Dragon NaturallySpeaking line as a developer. Their API is confusing, their speech recognition SUCKS, and their software bugs out in bizarre ways. It's also slow as a dog, and advanced functionality (like recognizing from wav files, as opposed to from a live audio stream) is so poorly implemented as to seem bolted on.

    And the worst part? Nuance has a virtual monopoly in realistically priced (read: "in a budget that a normal small-to-medium-sized business can afford") general-purpose speech recognition systems. If I recall correctly, they bought out Lernout and Hauspie's speech recognition products and IBM's old consumer-level speech-recognition stuff. So you can't take your business elsewhere; there is no "elsewhere".

    I loathe those guys.
  • by Narcogen (666692) <narcogen&narcogen,com> on Wednesday January 16, 2008 @07:43AM (#22064850) Homepage
    MacOS has had a built-in feature called Speakable Items that does exactly this, and as an option you can have it respond only to things said after a specific key word-- in essence, the machine's name. "Minion" would work fine.

    It is not true dictation. Essentially you create a script and give it a name. When your speech is recognized as the name of a corresponding script, the script is executed.

    You can even make scripts that required multiple inputs. Some of the built-in ones in the Mac OS 9 days were knock knock jokes.
  • by benmhall (9092) on Wednesday January 16, 2008 @09:38AM (#22065634) Homepage Journal
    My wife needed voice dictation software a year or two ago. She had been a Linux user. I gave her my PowerBook and bought iListen for her. It was terrible. And it was a resource hog. It used the Philips engine and, even with extensive training, was the pits. We even tried several high-quality mics to no avail.

    She went from my G4/1.5GHz/1.25GB RAM PowerBook running iListen to Dragon NaturallySpeaking 8 on an IBM ThinkPad T23. (P3 1GHz, 768MB RAM, WinXP.) The difference was night and day. Not only did Dragon run much faster on the lowly P3, but the quality of speech recognition was _much_ better. As a result of this, she's now back to being a Windows user with Dragon.

    At least it looks like our iListen purchase won't be a complete waste, as we can use it to upgrade to NaturallySpeaking for Mac. I'm glad that MacSpeech has killed iListen. It needed it. It was an embarrassment compared to Dragon.

    Speech recognition has been a big hole in the Mac's software line-up. It looks like that is finally coming to an end. Now if only someone would release something that works for Linux.* I know that we'd have paid $200 for something approaching Dragon 8's capabilities.

    ----
    *Yes, I know about IBM ViaVoice. Good luck getting that to work on any recent distribution. I also know about Sphinx. Unfortunately, it seems to be a perpetual research tool rather than an end-user program.
  • by samkass (174571) on Wednesday January 16, 2008 @10:36AM (#22066158) Homepage Journal
    Yeah, Apple's speech recognizer has very dissimilar goals to Dragon's (although both, if I recall correctly, got their start at Carnegie Mellon's speech labs). Apple is trying to build a speaker-independent, no-training-required recognizer that can handle short commands. Dragon doesn't care as much about speaker-independent, but requires accuracy over sentences and paragraphs. Very different algorithmic, HCI and optimization problems.

  • Re:At Last! (Score:2, Informative)

    by Chaset (552418) on Wednesday January 16, 2008 @01:28PM (#22068624) Homepage Journal
    Actually, almost 10 years ago, there WAS Dragon Naturally Speaking for Mac. I bought it, and its upgrade when it came out. (Unless my brain is totally whacked and it was some other voice recognition package for Mac) It came with a headset in the box, too. I'm sure that version is what that rep was talking about. It's funny... all these comments, and I didn't notice any high-scoring comments pointing out that there already WAS a voice recognition package for Mac years ago.
  • Re:At Last! (Score:3, Informative)

    by Slurpee (4012) on Wednesday January 16, 2008 @05:33PM (#22071760) Homepage Journal
    What you are thinking of is "Dragon Power Secretary" which was available for early Macs in the early 90s - but dropped (way before OS X). The WWDC announcement came when OS X was also being announced in 1999. The announced product at WWDC never came out.

    I was able to find this press release:

      WWDC--SAN JOSE, Calif. and NEWTON, Mass.--(BUSINESS WIRE)--May 10, 1999--

      Photo will be available at 2:30 pm EST on Associated Press via Business Wire

      Dragon Systems, Inc. and Apple(R) Computer, Inc. today announced that Dragon Systems will create and market Macintosh-compatible products based on Dragon NaturallySpeaking, the top selling retail speech product in the U.S.(a) Dragon Systems Chairman, CEO, and Co-Founder Janet Baker, Ph.D. announced the company's plans during the keynote presentation at Apple's annual World Wide Developer's Conference (WWDC) in San Jose.

      "It's great news for our customers that Dragon is bringing their world-class speech recognition software out on Macintosh," said Steve Jobs, Apple's interim CEO. "The underlying architecture of the Mac platform, with fast PowerPC processors and outstanding audio support, will make Macintosh the premier platform for Dragon NaturallySpeaking. Dragon's return to the Mac market is more evidence of the great business opportunities available on Macintosh for innovative developers."

      "We have received many requests for a Macintosh version of Dragon Naturally Speaking and working with Apple we're going to deliver a high quality speech solution for Macintosh users," said Dragon Systems Chairman, CEO, and Co-Founder Janet Baker, Ph.D. "Over the last year we have seen Apple bring out some very innovative products and we think Dragon Systems will offer the ideal speech recognition solution for anyone who wants to extend the capabilities of their iMac, Power Macintosh G3, or PowerBook G3."

    Dragon Systems' products for the Macintosh are planned initially for both American and British English, with the first U.S. product to be released later this year. French, German, and Japanese are also scheduled. Pricing, system requirements, and product specifications will be announced at product introduction.

    Dragon Systems has a long history of supporting products for the Macintosh platform. Previously, Dragon Systems offered Dragon PowerSecretary(tm), a discrete recognition dictation system for the Macintosh.
  • by Anonymous Coward on Wednesday January 16, 2008 @06:02PM (#22072174)
    The problem is that speech recognition won't work not only with IT specific terms, but with ALL named entities: family names, places, street names, etc...

    Speech recognition on totally free speech is still a dream, and is completely useless because you can type faster than what you speak. It might only be useful for doctors who want to take notes without needing to carry a laptop with them. Microsoft which employed many of the top speech researcher knows that pretty well. That's why they are not so active on that any more. Same for IBM.

    BUT Dedicated speech recognition (even in noisy environment) made tremendous progress, and don't need any training any more. It will be part of your mobile phones pretty soon along with speech synthesis: to help drivers (GPS instructions), order a pizza, dial numbers, route telephone call in hotlines, book tickets...
    This was made possible because the task is much easier, since the context is narrow, and the recognizer only expect a few choices from the user.

Premature optimization is the root of all evil. -- D.E. Knuth

Working...