Daniel Eran Dilger
Random header image... Refresh for more!

MacSpeech’s Dictate: High Quality Voice Command and Speech Recognition for the Mac

 Macspeechmw08
Daniel Eran Dilger
MacSpeech at this week’s Macworld Expo unveiled Dictate, its new speech recognition and voice command software currently in beta and slated for release mid February. The new product replaces and improves upon the existing iListen.

Dictate is now based upon the highly accurate speech recognition engine developed by Naturally Speaking; iListen was based upon technology licensed from Philips. MacSpeech supplies the user interface and rich integration with AppleScript and other Mac technologies. It is offering a preorder special of $149 on the $200 regular price, and also offers a $99 cross-grade price for existing users of iListen.

Speech Recognition Accuracy.
Representatives demonstrated the accuracy and intelligence of the new system by dictating live into the system. After being switched on, the system allows the user to both dictate and issue voice commands. It determines which you are doing by analyzing the context of words. Dictate only requires a 5 minute profile creation session, which profiles the mic used and then analyzes the speaker’s speech patterns and diction. In addition, the user can supply text that the software will analyze for unfamiliar words, and then speak those words to expand the system’s dictionary.

Continues: AppleInsider | MacSpeech’s Dictate: high quality voice recognition for the Mac

Technorati Tags: , ,

  • visualvoice

    This is my comment, right now I am using MacSpeech Dictate to comment on this thread. As you can see, there is hardly a problem other than my grammar. It took me about five minutes for the software to learn my voice and I’m just humming along and that’s about it. I’m a pretty slow typist, and I have latent Massachusetts accent that the software completely understands. Anyone who was wondering if MacSpeech is the real deal or not let me assure you that it is. I’m not associated with any one, I use tons of software and I used iListen as a comedy sketch. Because it was such a poorly written piece of software, that they should have given away MacSpeech Dictate to anyone who bought it. Instead of cross-grading. here I’ll quickly read to you from my company shipping policies so you can see a nonstop paragraph.

    shipping: accounts west of the Mississippi River were (or) in Florida are shipped via Federal Express. All those east of the Mississippi will be shipped via UPS ground. This is subject to change without notice. Please let your sales representative for (or) customer service agent know if you require overnight, today (2 day) or three days service. All Canadian accounts will be shipped via Purolator. mountain life is GSC registered and bills Canadian customers for GST, or brokerage, and any other applet of all (applicable) charges. This is also subject to change without notice.

    As you can see there are only a few mistakes, most of them because of my reading the paragraph so quickly and slurring a bit. I will read it once again, taking a little more time to enunciate.

    Shipping: accounts west of the Mississippi River or in Florida are shipped via a federal express. All those east of the Mississippi will be shipped via UPS ground. This is subject to change without notice. Please let your sales representative or customer service agent know if you require overnight today or three days service. All Canadian accounts will be shipped via Purolator. mountain life is GST registered and bills Canadian customers for GST, brokerage, and any other applicable charges this is also subject to change without notice.

    As you can see, the program liked it much more when I enunciated better, still, I was not talking like a newscaster, just a bit slower than I normally would talk. My final demonstration, will be to read from above in the blog. Just the final paragraph.

    Speech recognition accuracy.

    Representatives demonstrated the accuracy and intelligence of the new system by dictating live into the system. After being switched on, the system allows the user to both dictate an issue voice commands. It determines which you are doing by analyzing the context of words. Dictate only requires a five-minute profile creation session, which profiles the mic used and then an analyzes the speaker’s speech patterns and diction. In addition, the user can supply text that the software will analyze for unfamiliar words, and then speak those words to expand the system’s dictionary.

    As you can see, there was hardly a mistake.