I am very excited as I anticipate the launch of Dragon Naturally Speaking 10 from Nuance. I have been using version 9 since January of 2007, and I’m ready to see some new bells and whistles.

The new version is rumored to have a great deal more support for Blue Tooth devices and applications. I have not heard or seen any notes or rumors yet on increases in speed or accuracy.

I do not have a blue tooth connection on my own laptop yet, so for me to use that I’d have to pick up some USB blue tooth adapter probably. That said, I think I would really appreciate having the ability to use a wireless headset or microphone with Dragon Naturally Speaking. I like to pace just a bit when I’m thinking and composing and this could be a real boom to my work. Not to mention this could be useful for people that want to send off a few emails while working out on a tread mill or elliptical machine or something. All you need is a screen at a distance with the zoom set large enough to read from a distance.

These days with projectors and large flat panel monitors that is becoming easier and easier to set up all the time!

Sounds crazy, but I’ve tried it before and run into a few tangles (in the cord) so a wireless version might be kind of nice.  Who knows maybe by version 20, the program will be so good that it will be able to transcribe an infants ‘goos’ and ‘gas’ with microphones sewn in the crib bedding so that new parents can receive a text message letting them know that their little one is hungry or needs some fresh air.  Its not always easy to see where new technologies will take us, but it seems practical to always leave conceptual options open.

Page Popularity for Site: 3% [?]

I’m trying a new experiment this evening with Dragon Naturally Speaking and the online Social Networking service Utterz.  I’m trying to take the .MP3 file generated by Utterz when I phoned into their service and left a message from my cell phone. 

The message could likely be considered to be of the quality of a digital voice mail message.

I then downloaded the Utterz mp3 file to my computer and ran it through my Dragon Naturally Speaking profile to transcribe the file into text.  Here are a couple things that I learned:

1. It is possible to get the file and run it through transcription
2. The transcription was less than successful.  Accuracy was low and the likely culprit is the quality of the audio (recorded via cell phone and possibly at less than optimal bit rate for dragon naturally speaking  The bit rate was actually 64kbs which should have been fine if anything maybe a little high.)
1. Utterz probably uses a bit rate slightly on the low side to serve thousands of audio messages
2. Dragon Naturally Speaking works best with a higher MP3 bit rate (32 - 48 kbs or better)
3. When I left the message, I did not leave a several second pause at the beginning before I started to speak which can sometimes make a transcription from a file or device skip the first few words in Dragon Naturally Speaking 9.

Follow Ups

I’m going to next try to create an audio dictation on my pocket recorder.  Then upload that audio to Utterz.  I will then run the original file through transcription and separately download the mp3 file from the utterz site separately and run it through as well.

I’m going to do this just to see if the audio quality is adjusted after upload.  I doubt that it is, but I just want to check.

Tip

If you happen to create an audio file that you want transcribed and you forget to leave a few seconds of space at the beginning. You can use the free program audacity to insert a space of several seconds into your audio file and then generate a new mp3 file.

If a file transcribes poorly, you might try converting the file to a different KBS rate.  I mentioned that I seem to get the best results at about 48kbs.  I tried this tip with my own file and it did improve the accuracy (although not enough as I was still getting word substitution errors that were nonsensical like child insurance for ‘file in this instance’).

Page Popularity for Site: 3% [?]

About a year and a half ago, during the winter of 2007, I came across this great video demonstrating Dragon Naturally Speaking 9.  I had used Dragon Naturally Speaking 3 or 4 about 10 years earlier and my impression back in the 90’s was one that voice recognition and the hardware that ran it, wasn’t ready for the masses.

Dragon Naturally Speaking Official Demo Video

This is What Sold me on the Program and in reality it works this well if not better!

This video helped to show me that both the software and the hardware had come a long way.  It got me to get off the fence, and pay about $150 for a software program that would enable me to type at 150 words per minute.

I can no longer find this particular video on the actual Nuance website, but I did find a version on YouTube and uploaded it here. In my opinion it does a very good job of providing an example of just what the software is capable of doing for any user.

I’m even thinking about trying to recreate this video to show that its not ‘just an ad’ and that the capabilities in this demonstration are actually possible. I have a flat panel monitor that is not quite as large as the one shown in the video. I’m going to try and get a plasma tv mount for it and set something up in my wifi dock office to show this off.

Page Popularity for Site: 5% [?]

	Andrew Ian Dodge is a 37 year old American expat living and working in London. He is a writer, author, novelist, blogger, political consultant  (his full time work) and the lyricist/frontman for Growing Old Disgracefully.
Website(s): www.andrewiandodge.com www.disgracefulmusic.com Profile: Andrew Ian Dodge on LinkedIn	He has been writing mythos stories for many years and has written an Idiots Guide to the Mythos.

Here are Andrew’s initial impressions of MacDictate along with some Screenshots of the User Interface

I have been asked to review MacDictate and use MacDictate to write my review . Now I bought MacDictate for my father but it is becoming rather useful for me as I am going through chemotherapy and have suffered from painful fingers. This affliction meant that I was unable to type anything longer than a sure I am chat. I was interested to see how easy it would be to use this sort of programme for someone who writes as much as I do.

I have been planning to buy MacDictate for my father who is not as good a typist and is rather sick of his hunt and pecking. I was surprised and pleased that MacDictate was so easy to set up. Now it might be rather unfair of me owing to the fact that I have both radio and podcasting experience. In fact I have been both behind and in front of the microphone many times. One learns very quickly to speak clearly if one is trying to get a point across on radio or television. It also may help that I have a so-called transatlantic accent which has a limited amount of regional dialect.

The package is quite an impressive one including a microphone headset and the software. The programme is rather easy to install and the training mechanism does not take too much effort to get right.

This does not need spending hours and hours training the software and you can get right to work fairly quickly.

My experience with such programmes goes back a few years and I’m impressed at the improvements made in MacDictate for the Macintosh with the Dragon Naturally Speaking voice recognition engine. Now I’ve only had it for a very few days and have yet to fully use all its varied abilities. However initial impressions bowled from installation and initial use a very good indeed. From these initial impressions I would recommend this to anyone in need of a decent piece of dictation software.

….

so there are some initial glimpses of MacDictate.  We hope to have some video capture of the program in action before too long.  We are also chasing down a story about video gamers using dictation to capture their moves, cheats, and conversations for publication when gaming on platforms such as the PS3 and XBox 360.

Page Popularity for Site: 15% [?]

I learned a new thing about Dragon Naturally Speaking 9 when I transcribed multiple MP3 files into text this evening. 

I had 6 documents (recordings) that I needed to have transcribed.  I opened up Dragon Pad (the Word Pad like program that comes with Dragon Naturally Speaking).  I then used the Transcribe Recording program to select MP3 sound files of my voice one at a time and have them transcribed into text within the same document.

It was a slightly repetitive process as I do not have a batch transcription capability with my version of Dragon Naturally Speaking 9.  (this may come with the mobile version, but I can not attest to that).

The interesting thing that I learned

After completing 6 transcriptions, with the text transcribed onto the same document, I was able to go back and select text from any of the 6 transcriptions and play back the voice file that went with the transcription. 

Plus, I could even correct that text to help train my computer for greater accuracy.

Finally, the original MP3 files did not have to remain on my computer.  I was able to play back the voice with the text, even after I had removed the original MP3 file from my computer.

The MP3 file was actually on my pocket recorder stored in flash.  I disconnected the card from the USB and could still play the file back.  This signified that the transcription process actually copied the sound file into or with the dragon pad document.

How Long does the Sound File stick with the Document?

The sound file and ability to listen to the voice with the play back function remained until I closed the document. I tried saving the document, closing the document and then re-opening the document in Dragon Pad.

Once it was reopened, I could no longer listen to the voice file that went with the transcribed text.

All in all I was impressed with this functionality as I tested it and learned some of the new boundaries.  Its not a deal maker or breaker for this software, but under certain circumstances it is useful to understand.  Its not so great that I’m going to call up my futures broker in the middle of the night and go long on Nuance stock or something.

However, if you ever run into a situation where your computer crashes and a document gets closed down prematurely, it would be my advice to simply run the original voice file through the transcription again and start over again if you need the ability to go back and compare the text to the original voice file.

Page Popularity for Site: 26% [?]