Audio Transcription Technology

Audio transcription technology has made a jump in quality, but it is not cheap. The language translator community is getting into this now, and webcasting interfaces with this technology.

1. Here is a product feature matrix for Dragon 10
http://www.nuance.com/naturallyspeaking/resources/product-matrix.asp

Dragon 10 Professional
http://www.nuance.com/naturallyspeaking/products/professional.asp

Dragon Audiomining
http://www.nuance.com/naturallyspeaking/products/audiomining.asp







2. Multi-Lingual and Enhanced Use of Dragon

The multilingual version of Dragon includes English voice recognition as well as an option. You just need to create a new profile and set its second language.

In practical terms, when you want to switch from French to English, you will just need to right-click the Dragon icon next to the clock and select (let's say) "Sheila français" instead of "Sheila English".

However, it will be seen by the system as a completely separate user and will not share data and terminology with the other. Actually, it will even have to be trained from scratch as if it was different person.

It will also take a bit of time, as it saves the previous profile data before opening the new one. I wouldn't really recommend to switch back and forth.

To sum up:

Q: Does it produce high-quality UK English

A: I would say so. It come with British/US/Australian/SEAAsian tailored dictionary files, and I guess these languages are really their core business...

Q: Is dictating in both English and French possible in the same document?

A: It is possible if you switch profile, but not practical due to save/load time.

Q: Put in simple, non-computer expert terms, what are the advantages of the preferred version over the standard? Is it worth the extra 100€?

A: Dragon is available in a number of versions. The Standard edition ($100) has the same accuracy as the others, but it’s just for bare-bones dictation. To get the more advanced goodies described in this review — the natural-language commands, Bluetooth mikes and recorders — you need the Preferred edition ($200). It also lets you set up voice macros that type out boilerplate text. For example, you can say, “Buzz off,” and it will type: “Thanks for thinking of me! Unfortunately, I’m afraid I’m unable to accept your kind offer at this time.”

http://www.nytimes.com/2008/08/07/technology/personaltech/07pogue.html?pagewanted=1&_r=2

3. Google has added speech recognition capability in some YouTube videos that enables you to search for text spoken in these videos.

http://googleblog.blogspot.com/2008/07/in-their-own-words-political-videos.html

4. Various other tips and services towards "wav-to-text" transcription, video search and administration, and shownote taking are reported within the following link list too:

http://www.blinkx.com/
http://trafcom.typepad.com/blog/2007/01/podcasting_secr_1.html
http://www.veotag.com/
http://www.clipblast.com/
http://www.pixsy.com/
http://jott.com/

5. Streaming - Transcribing - Blogging

http://www.webcastacademy.net/node/2068

In conjunction with Synchrone Web-Based Author < > Translator Processing, a significant productivity gain may be achieved.

I hope to get this process running soon...

http://collaborative-translation.ning.com/group/transcription