RE: How do they record the actors for voice response systems

Subject: RE: How do they record the actors for voice response systems
From: "Downing, David" <david -dot- downing -at- fiserv -dot- com>
To: "Fred Ridder" <docudoc -at- hotmail -dot- com>, <techwr-l -at- lists -dot- techwr-l -dot- com>
Date: Wed, 1 Apr 2009 10:15:40 -0500

Well I'm sure some of them use snippits of real voices. I think I can
tell the difference between a real voice and a synthetic one - although
the synthetic ones are admittedly getting more realistic-sounding all
the time.



David Downing

Senior Technical Writer

Credit Union Solutions

Fiserv





________________________________

From: Fred Ridder [mailto:docudoc -at- hotmail -dot- com]
Sent: Wednesday, April 01, 2009 11:08 AM
To: Downing, David; techwr-l -at- lists -dot- techwr-l -dot- com
Subject: RE: How do they record the actors for voice response systems



David Downing asked:

> There's something I've always wondered about voice response systems,
and I was wondering if anyone here has had firsthand experience
constructing one and so could answer my question. My question concerns
the systems that recite phone numbers you just dialed, your bank
balance, dates, etc. -- "The number you have reached -- nine - two -
three - four - five - six - two -- has been disconnected because the
customer didn't pay his bill," "Your pathetic bank balance is -- two -
dollars - and - ninety - three - cents." How do they go about recording
the raw material for those snippets they piece together so that the end
result reasonably approximates natural intonation? And I have to say,
some systems do it a lot better than others.

The voice is not an actor. It's synthetic, generated by a text-to-speech
(TTS) algorithm. Same thing with the voice that spew directions from
dashboard GPS devices.

-Fred Ridder

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

ComponentOne Doc-To-Help 2009 is your all-in-one authoring and publishing
solution. Author in Doc-To-Help's XML-based editor, Microsoft Word or
HTML and publish to the Web, Help systems or printed manuals.
http://www.doctohelp.com

Help & Manual 5: The complete help authoring tool for individual
authors and teams. Professional power, intuitive interface. Write
once, publish to 8 formats. Multi-user authoring and version control! http://www.helpandmanual.com/

---
You are currently subscribed to TECHWR-L as archive -at- web -dot- techwr-l -dot- com -dot-

To unsubscribe send a blank email to
techwr-l-unsubscribe -at- lists -dot- techwr-l -dot- com
or visit http://lists.techwr-l.com/mailman/options/techwr-l/archive%40web.techwr-l.com


To subscribe, send a blank email to techwr-l-join -at- lists -dot- techwr-l -dot- com

Send administrative questions to admin -at- techwr-l -dot- com -dot- Visit
http://www.techwr-l.com/ for more resources and info.

Please move off-topic discussions to the Chat list, at:
http://lists.techwr-l.com/mailman/listinfo/techwr-l-chat


References:
How do they record the actors for voice response systems: From: Downing, David
RE: How do they record the actors for voice response systems: From: Fred Ridder

Previous by Author: How do they record the actors for voice response systems
Next by Author: RE: How do they record the actors for voice response systems
Previous by Thread: RE: How do they record the actors for voice response systems
Next by Thread: Re: How do they record the actors for voice response systems


What this post helpful? Share it with friends and colleagues:


Sponsored Ads