W3C home > Mailing lists > Public > www-voice@w3.org > January to March 2004

RE: Baseline and Relative Prosodic Attributes

From: Daniel Burnett <burnett@nuance.com>
Date: Fri, 20 Feb 2004 16:25:43 -0800
Message-ID: <ED834EE1FDD6C3468AB0F5569206E6E902732354@MPB1EXCH02.nuance.com>
To: "david.descamps-be" <david.descamps-be@laposte.net>, "www-voice" <www-voice@w3.org>
Sorry for the delay in responding.  My comments are in-line below (preceded by DB>>).
-- Dan Burnett

-----Original Message-----
From: david.descamps-be [mailto:david.descamps-be@laposte.net]
Sent: Tuesday, January 20, 2004 5:39 AM
To: www-voice
Cc: david.descamps-be
Subject: Baseline and Relative Prosodic Attributes



Relative changes in prosodic parameters should be carried across voice changes. However, different voices have different natural defaults for pitch, speaking rate, etc. because they represent different personalities, so absolute values of the prosodic parameters may vary across changes in the voice.


if I understand that, the synthesis processor must make the difference between, for example, baseline pitch change and relative pitch change?  

 DB>>  Yes, the processor must differentiate between absolute changes of the baseline and changes relative to the baseline.

In the "prosody" element: when you change your pitch by

- a number followed by "Hz",  you change the baseline pitch 

DB>> This is correct. 

- and a relative change or "x-low", "low", "medium", "high", "x-high", or "default", you change the relative pitch. 

DB>> This is only correct for relative changes.  "x-low" through "x-high", etc. are absolute pitch changes. 

Is It right?

If it is, does a baseline change in a "prosody" element cancel previous relative change?

DB>> Yes. Note that it would only cancel relevant relative changes. For example, setting the baseline pitch would not reset relative pitch *range* changes. 

 DB>> Although it is easy to construct silly or bizarre example combinations of absolute and relative changes, most of which will hopefully be ignored by intelligent processors, the goal of this separation was to simplify the case where an author has increased the tempo/pitch/etc. of a voice and wishes that same relative change to apply when a small amount of text in another language (and voice) is embedded in the stream.


Accédez au courrier électronique de La Poste : www.laposte.net ; 
3615 LAPOSTENET (0,34EUR/mn) ; tél : 08 92 68 13 50 (0,34EUR/mn) 
Received on Friday, 20 February 2004 19:25:45 UTC

This archive was generated by hypermail 2.4.0 : Friday, 17 January 2020 23:03:48 UTC