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% [?]

Today I wanted to run a quick little test with Audacity and Dragon Naturally Speaking.  Essentially this is a proof of concept test.  I’m working to prove:

• That both dragon naturally speaking and Audacity can operate at the same time
• that a podcast can be created, recorded and transcribed at the same time
• that regular amplified microphones can work as good as the noise cancellation microphone that comes with dragon naturally speaking 9 preferred (that’s a mouthful of a title!)

Here’s my microphones (The Tapco mixing board is off camera)

Understand there are times when I want to use the dragon headset, but when I’m at home, sometimes I don’t want the distraction or I want the podcast headphones on my ears and not the dragon headphone.

Here’s the podcast and recording of the session:

Here’s the text from my transcription:

This afternoon I’m testing out a microphone system running through a mixer board and plugged into my laptop. I’m actually running dual microphones, so I’m being captured in stereo is then routed to my laptop via Mono. (I’m not an audio engineer so I have no idea what I’m talking about just using the best words I can think of to describe what I’m doing.)

Why am I doing this?

I wanted to see if I could use the microphones in this way such that I don’t have a headset on my head. I’m about 6 inches away from my microphones which are sitting on my desk. You can call us and experiment. I’m going to expanding this experiment in the future to run Dragon NaturallySpeaking and audacity, a podcasting software, so that I can determine if I can podcast and transcribe my taxed at the same time.

After trying a quick test, I’m now using Dragon NaturallySpeaking and audacity at the same time. As I do this I’m going to stop using punctuation such as words like ‘Period’ and ‘Coma’ because I’m actually recording a podcast with audacity.

It’s a hard habit to break! Anyway this is actually working fairly well. I’m recording the words on a Word document with Dragon NaturallySpeaking and I’ve got audacity running on a separate screen I can see that my voice is being captured perfectly on audacity and I can see that my words (are) being captured almost perfectly in Dragon NaturallySpeaking. 

There is one issue though, if I slip in and out of a particular screen meaning out of Word and into audacity to pause or stop Audacity then my words are no longer captured in Microsoft Word as the active screen has to be continually open for Dragon NaturallySpeaking to capture the words.  It’s just a little thing but I could see some situations where I could become a problem.

So there’s the demo.  Its been a while since I tried something like this.  I had used the microphones before just with DNS9, and I had used DNS9’s headset with audacity.

Note, I’m also publishing this podcast through Utterz and then embedding the audio into the blog post after the fact. 

In the future, I suspect that I might use the headset more often when I’m traveling as its not practical to take my mixing board and other gear on a plane, to the beach and you don’t see too many podcasters on cruises with a full radio studio or anything like that.

Page Popularity for Site: 33% [?]