MacSpeech Dictate Updated to 1.3

We were privileged to be the first dealer to test MacSpeech Dictate when it premiered at MacWorld in 2008. It was fast, accurate and wonderfully elegant. Yet, while it was built on the Dragon NaturallySpeaking engine, it lacked many of the more important features of Dragon such as corrections and phrase training.

With the new 1.3 update of Dictate, these features are not only added, they work very, very well. We've been testing this new update - which you can download through the software updating function of Dictate - and we're impressed!

There are several new enhancements to MacSpeech Dictate 1.3:

"Cache Document" and "Cache Selection" commands

The "Cache Document" command is significantly revamped to be functional in other applications. This command places the entire text from a document into Dictate's cache. The "Cache Selection" command places selected text into cache. These commands allow a user to effectively navigate and edit other documents by voice.

Searchable Help

The help "book," available under the Help menu, is indexed and searchable.

Menu Bar Status Item & Dock Icon Badging

Microphone status indicators have been added to the Dock icon and the menu bar. The appearance of the Status item is controlled via Preferences.

"Press the Key" Commands

"Press the Key" and "Press the Key Combo" commands will input the specified keyboard keys. You can also use modifiers, such as Command, Control, Option and Shift.

"Cancel Training" Command

A "Cancel Training" command has been added to the Available Commands window. Use this command to close the Recognition window.

Recognition Window Output

Recognition window output is now handled without auto-formatting. If a user adjusts the capitalization of a word in a Recognition window entry, Dictate will not change it to match context. To adjust capitalization for that word in the document, use a "Lowercase the Word" or "Capitalize the Word" command.

Removed "Force Quit this Application" command

Oops! Seems like Dictate, at times, would mis-interpret a phrase and users where finding their applications quitting without saving. To force quit using Dictate 1.3, you can dictate "Press the Key Combo Command Option Escape."

There have also been several "fixes" as part of the 1.3 update:

• Phrase training a word or phrase and replacing it with a longer word or phrase would sometimes result in a failure of the subsequent use of "Go to End."
• Application that do not have certain expected bundle information will no longer cause Dictate to crash when launched.
• If there is no dictation area available and the Recognition window is the target, a message is displayed in the Recognition window asking the user to open a new document or select a text area.
• Continuous rapid switching dictation modes no longer crashes Dictate.
• The command "Train Vocabulary from Selection" now copies the indicated contents to Dictate for training.
• "About this Application" now works properly.
• "Capture (Selection/Screen)" now functions as intended.
• Under some circumstances if a user issued two commands far enough apart they would be considered separate commands but within a particular time frame and Dictate would crash. Not any more.

If you are a Macintosh user and would like to make your writing more efficient, you should definitely consider MacSpeech Dictate. We're sold on it, and very excited to a be a leading dealer for this product.

Note: the version we offer at American Dictation includes a higher quality headset than the boxed version found in more retail outlets. We have found a significant improvement in Dictate's accuracy with the use of a better headset. Additionally, we have had great success in using the wireless Plantronics CS50 USB headset with Dictate.

Speech-Recognition for Interviews

Every day, we get phone calls and e-mails from people hoping to use speech recognition software to transcribe interviews, lectures, or meetings. It seems so reasonable to assume that today's technology could easily take a digital voice recording of two or more people and translate that into an accurate text representation.

Sadly, that is not the case. The supercomputers of the CIA and NSA notwithstanding, today's most popular voice to print software programs are unable to translate the speech of more than one person with any degree of real usability for several reasons:

1. Speech recognition software should be trained for the speaker's voice. While Dragon NaturallySpeaking promotes that "no training is necessary," allowing the software to adapt its algorithms to the speakers voice, speaking style, and writing style can tremendously improve the accuracy of the software.
2. It is impossible for speech recognition software to discern the difference speakers in a recorded conversation. To the computer all sounds are analyzed to find signs of spoken words. The software can not, at one moment, recognize Speaker A and the next moment recognize Speaker B. It will try to decipher all spoken words using whatever singular user profile has been selected in the software for transcribing.
3. Speech recognition software is really a dictation tool, rather than a transcription device. That is to say, it works best when the speaker "dictates" to the software. Accurate dictation includes punctuation, spellings of potentially unknown words or names, and uses complete sentences and phrases. When was the last time you heard two people talking together in complete sentences, and speaking intended punctuation?
   

I'm using speech-recognition software to write this blog. Before I dictate, I formulate the sentences mentally, then speak them evenly and with punctuation into my wireless headset. Almost instantly, the phrase I have just completed appears as text on the screen. And with amazing accuracy. The accuracy is due to the fact that I trained my speech recognition software (in this case MacSpeech Dictate) to understand how I dictate.

Speech recognition software works amazingly well. But, for its intended purpose.

There have been some of our customers who have employed creative workarounds for the purpose of converting interviews to text without typing. One of the most common we hear of, is where the interviewer listens to a recording of the interview in one ear, and dictates what they hear into the speech recognition software. This gives them the ability to add subject names and formatting instructions lacking in the original recording. This method also helps clarify the conversation where both parties were talking at the same time (you can imagine how inaccurate any type of automated transcription would be).

As technology pushes the limits of power and speed in personal computers, we should someday expect to see speech recognition systems that come close to replicating the recognition capabilities of the human brain. Realizing the an enormous capacity and sophistication of our brains, I cannot imagine that happening anytime soon.

Technorati Profile