Using Speech Recognition Software to Help Create Accessible Resources

We've been working on creating more audio and video resources recently, and we've wanted to develop a process to allow us easily and quickly create transcriptions of them.

Transcriptions, we think, would be a step towards helping make resources accessible for all potential users. Not only that but it's nice to have a transcription so people can scan the contents to see if they want to spend time watching a video.

We've just purchased a copy of Dragon Naturally Speaking 9 Preferred, which transcribes audio files in several formats:

.wav
.vox
.mp3
.wma
.sri

This is suitable for us as the software we are using for creating video (Premiere Pro 1.5) and screencasts (Camtasia Studio 3) both allow export of the audio as .wav files.

To test it I transcribed a short (134 second) video manually. This contained 391 words and took me about 20 minutes to transcribe (without any special transcription software or peddles).

Dragon transcribed this (before I trained it to recognise my voice) and it got 296 words right. After 30 minutes general training it got 308 words correct, and adding special words that I used in the videos but which weren't in Dragon's vocabulary pushed that to 311 words.

To correct this final file took about 10 minutes, indicating that this way of creating transcriptions would half the time it has been taking me to create transcriptions.

Spending 30 minutes training Dragon to recognise my voice raised the accuracy from 76% to 80%, which doesn't sound like much but I think would be worth asking staff to train Dragon if they were creating a lot of resources that were to be transcribed.

In conclusion, this doesn't look like it will make transcriptions almost automatic, and that would be important if we were to transcribe everything. However it will help us create transcriptions when we want to.

Looking online at transcription services, they charge from about £0.60 per minute for 1-2 speakers to £1.25 per minute for 5 or more speakers. Outsourcing to these services might be a good solution if we have too much work in this area.

Web2.0 Explained

The Machine is Us/ing Us

This is a great video created by Michael Wesch, Assistant Professor of Cultural Anthropology at Kansas State University.

The video introduces the Web 2.0 concept,("..the so-called second wave of Web-based services that enables people to network and aggregate information online"*), and highlights the impact it is having in less than 5 minutes.





*A Lesson in Viral Video, an article written by Elia Powers back in Febuary for Inside Higher Ed, gives some background to Wesch's video.

The Medieval Helpdesk

Introducing new concepts has always been difficult...technology is no different...

This is a great video illustrating this exact point:

SOLSTICE Conference 2007: One Minute Mix

This video is a one-minute encapsulation of the May 2007 SOLSTICE conference.

SOLSTICE is Edge Hill's Centre for Excellence in Teaching and Learning. It's aim is to help develop a method of course delivery that has the use of technology integrated into it, rather than added on to it.

Using YouTube to Host Learning Objects

Some members of staff here have been talking about using video sharing sites like YouTube to host their videos, so I thought that I'd look into this a bit more so see what I could learn.

I've uploaded my 'Screencasting with Camtasia' screencasts to YouTube.

Screencasting Using Camtasia: 01 - Introduction
Screencasting Using Camtasia: 02 - Installing
Screencasting Using Camtasia: 03 - Microphones
Screencasting Using Camtasia: 04 - Starting a Recording
Screencasting Using Camtasia: 05 - After Recording
Screencasting Using Camtasia: 06 - Producing
Screencasting Using Camtasia: 07 - Tips
Screencasting Using Camtasia: 08 - Accessibilty

So, what are the benefits and drawbacks of releasing materials this way, over putting them on the streaming server?

Benefits:
-Should be no access problems because YouTube uses Flash video and almost everyone has the Flash plugin installed.
-Easy to embed the videos in your WebCT area.
-Doesn't use the limited space on the streaming server.

Drawbacks:
-Quality is almost always lower after it has been re-encoded during the upload to YouTube, although the 'What's the best format to upload for high quality?' page will give you advice on the formats to save your video in for the best results.
-YouTube seems to cut the end off my videos - you need to remember to leave a bit extra video at the end to compensate.
-Can't update videos on YouTube without uploading another version and changing the link. We can do that easily on the streaming server.

Anything else I've missed?